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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing the word "common."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to commonalities or shared traits among subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gur
    -0.79
    icer
    -0.69
    graded
    -0.67
    eki
    -0.67
    asus
    -0.66
    oby
    -0.66
    apo
    -0.66
    zzy
    -0.65
    ithing
    -0.64
    dot
    -0.62
    POSITIVE LOGITS
    wealth
    0.79
     resemblance
    0.75
    alities
    0.73
     decency
    0.70
     amongst
    0.70
     relation
    0.69
    SHIP
    0.69
    places
    0.69
     resemb
    0.65
    FIELD
    0.65
    Act Density 0.021%

    No Known Activations