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

    Neuronpedia

    INDEX
    Explanations

    statements from different people

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating a refusal or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Outside
    -0.54
     Moroc
    -0.52
     Coliseum
    -0.51
    ichever
    -0.51
    School
    -0.51
    romeda
    -0.50
     Pearce
    -0.50
    eday
    -0.50
     Pixie
    -0.49
    Gray
    -0.49
    POSITIVE LOGITS
     hereby
    0.77
     largeDownload
    0.74
     nevertheless
    0.71
    pmwiki
    0.71
     nonetheless
    0.65
    ']
    0.62
     surely
    0.62
     adv
    0.61
     replied
    0.58
    ');
    0.58
    Act Density 0.537%

    No Known Activations