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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating action or decision

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "taking" or "not taking" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lehem
    -0.70
    naire
    -0.69
    alam
    -0.67
    éŃĶ
    -0.67
    icol
    -0.66
    fw
    -0.66
    女
    -0.65
    lex
    -0.65
    ingen
    -0.64
    nell
    -0.64
    POSITIVE LOGITS
     kindly
    1.16
     advantage
    0.96
     anymore
    0.94
     lightly
    0.88
     responsibility
    0.86
     seriously
    0.86
     sides
    0.85
     aback
    0.82
    aways
    0.81
     heed
    0.79
    Act Density 0.049%

    No Known Activations