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

    Neuronpedia

    INDEX
    Explanations

    phrases or questions questioning or expressing concern about a particular issue

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express negation or questions about responsibilities and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptic
    -0.76
    ENE
    -0.72
    archy
    -0.72
    okingly
    -0.69
    zer
    -0.68
     Finder
    -0.68
     Appears
    -0.68
    adel
    -0.67
    rompt
    -0.67
    onym
    -0.66
    POSITIVE LOGITS
     adequately
    1.10
     adequate
    0.78
     properly
    0.77
     heed
    0.74
     anymore
    0.73
    unda
    0.72
     timely
    0.71
     acknow
    0.71
     bothered
    0.71
     mathemat
    0.71
    Act Density 0.788%

    No Known Activations