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

    Neuronpedia

    INDEX
    Explanations

    references to violent and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and criminal acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯ãĥ³
    -0.63
    erenn
    -0.62
    retty
    -0.60
    eday
    -0.57
    irteen
    -0.56
    schild
    -0.56
     anecd
    -0.56
    mittedly
    -0.54
    achus
    -0.53
    undrum
    -0.53
    POSITIVE LOGITS
     thereto
    0.80
     thereof
    0.79
    ↵Âł
    0.78
    )?
    0.76
     doesnt
    0.74
     didnt
    0.74
     dont
    0.74
     them
    0.73
     theirs
    0.73
     hers
    0.72
    Act Density 1.267%

    No Known Activations