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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.84
    theless
    -0.78
    anwhile
    -0.73
     physic
    -0.70
    éĹĺ
    -0.68
    etheless
    -0.67
     captcha
    -0.67
    */(
    -0.66
    ä
    -0.66
     sanity
    -0.64
    POSITIVE LOGITS
    leys
    0.87
    iest
    0.82
    onian
    0.80
    venth
    0.79
    hest
    0.78
     Nebula
    0.75
    ounding
    0.75
    osphere
    0.74
    DC
    0.74
    agame
    0.73
    Act Density 0.417%

    No Known Activations