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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, likely related to news events or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    names of people involved in legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umph
    -0.69
    thood
    -0.68
     Deadline
    -0.67
    ibilities
    -0.66
    Available
    -0.66
    clusions
    -0.65
    lance
    -0.65
    erning
    -0.65
    paren
    -0.65
    alg
    -0.64
    POSITIVE LOGITS
     violated
    1.31
     behaved
    1.19
     acted
    1.19
     interfered
    1.18
     lied
    1.13
     stole
    1.12
     unlawfully
    1.10
     smelled
    1.09
     misled
    1.09
     inappropriately
    1.09
    Act Density 0.346%

    No Known Activations