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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and events

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases related to events prior to an incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erenn
    -0.83
    anges
    -0.74
    umeric
    -0.74
    ä¸Ĭ
    -0.70
    gae
    -0.67
    ¥
    -0.67
    ographies
    -0.65
    ı
    -0.65
    gem
    -0.64
    à©
    -0.63
    POSITIVE LOGITS
     arra
    0.98
     arrest
    0.89
     Friday
    0.86
     Tuesday
    0.86
     Wednesday
    0.85
     incident
    0.85
     filming
    0.85
     Thursday
    0.83
     arrests
    0.82
     Monday
    0.81
    Act Density 0.231%

    No Known Activations