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

    Neuronpedia

    INDEX
    Explanations

    actions or events related to legal matters and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in legal proceedings or criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    growth
    -0.73
    æĦ
    -0.72
    ysc
    -0.69
    rame
    -0.64
    ::::::::
    -0.63
    ¥µ
    -0.61
     digestion
    -0.60
    ãĥ¤
    -0.60
     Checking
    -0.60
     differentiation
    -0.59
    POSITIVE LOGITS
     pleaded
    1.83
     pled
    1.77
     plead
    1.62
     faces
    1.49
     confessed
    1.39
     testified
    1.33
     sentenced
    1.32
     denies
    1.29
     admitted
    1.29
     appealed
    1.28
    Act Density 0.227%

    No Known Activations