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

    Neuronpedia

    INDEX
    Explanations

    activities involving social interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.68
    ights
    -0.57
    mage
    -0.55
    ati
    -0.54
    BUG
    -0.52
    handler
    -0.52
    ouf
    -0.51
    ajor
    -0.51
    >[
    -0.51
    omsky
    -0.51
    POSITIVE LOGITS
    stood
    1.33
     regard
    1.24
     regards
    1.24
    standing
    1.07
     impunity
    0.96
     respect
    0.96
    drawn
    0.93
    draw
    0.92
    holding
    0.86
     dignity
    0.73
    Act Density 0.328%

    No Known Activations