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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal relationships or interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of "pe" words, likely denoting "people" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.79
    enegger
    -0.72
     GOODMAN
    -0.69
     Pulse
    -0.67
     guiActiveUnfocused
    -0.67
    footed
    -0.66
     Reincarn
    -0.65
    oldemort
    -0.65
    picture
    -0.64
    OME
    -0.63
    POSITIVE LOGITS
    ggy
    1.04
    asant
    1.00
    eps
    1.00
    gging
    0.99
    pperc
    0.99
    aking
    0.96
    achy
    0.96
    eking
    0.95
    eper
    0.93
    ptic
    0.92
    Act Density 0.009%

    No Known Activations