Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to something being considered inappropriate or outside of acceptable limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases or expressions involving the concept of being "off" something, indicating separation or divergence.

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    Following the word "off"

    np_acts-logits-general · gemini-2.0-flash

    idiomatic expressions with "off"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.64
    étit
    -0.64
     textStatus
    -0.62
     Erskine
    -0.59
    fulness
    -0.59
    Parcelize
    -0.59
     Winaray
    -0.59
    er
    -0.58
    Życiorys
    -0.58
    siasme
    -0.57
    POSITIVE LOGITS
    screen
    0.70
     kil
    0.68
    shoot
    0.68
     balance
    0.65
    beat
    0.65
    springs
    0.64
     course
    0.63
    site
    0.63
    course
    0.62
     '').
    0.62
    Act Density 0.065%

    No Known Activations