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

    Neuronpedia

    INDEX
    Explanations

    mentions of criminal activities, such as murders, stabbings, shootings, and assaults

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criminal activities and legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.73
    âĹ¼
    -0.71
    ëĭ
    -0.70
    fortunately
    -0.67
    omever
    -0.67
    Footnote
    -0.66
    pron
    -0.65
    APTER
    -0.65
    Ó
    -0.62
    inarily
    -0.61
    POSITIVE LOGITS
     probe
    0.80
     feds
    0.75
     shuts
    0.74
    =>
    0.74
     Says
    0.72
     accuser
    0.70
     amid
    0.68
    Adds
    0.67
     Replay
    0.67
     Probe
    0.67
    Act Density 0.301%

    No Known Activations