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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or criminal activities involving communication

    oai_token-act-pair · gpt-3.5-turbo

    co-occurrences of the word "and" with various other terms related to communications and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.70
    wic
    -0.66
    ondon
    -0.66
    imester
    -0.66
    arak
    -0.65
    ummer
    -0.63
    WR
    -0.63
    ukong
    -0.62
    urch
    -0.62
    Manager
    -0.61
    POSITIVE LOGITS
     other
    1.13
     assorted
    0.95
     others
    0.81
     possibly
    0.79
     various
    0.75
     occasional
    0.73
     unspecified
    0.72
     logistical
    0.71
     several
    0.69
     elsewhere
    0.68
    Act Density 0.469%

    No Known Activations