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

    Neuronpedia

    INDEX
    Explanations

    words related to news reporting and journalism

    oai_token-act-pair · gpt-3.5-turbo

    reporting and communication verbs associated with updates or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.77
    owers
    -0.69
    thing
    -0.64
    productive
    -0.62
    folk
    -0.62
    riv
    -0.62
     valve
    -0.60
    leness
    -0.60
    oÄŁ
    -0.60
    lection
    -0.60
    POSITIVE LOGITS
    ometimes
    0.92
    hirt
    0.82
    ilver
    0.75
    olate
    0.73
    omething
    0.73
    psey
    0.65
    ebted
    0.63
     herself
    0.61
    hift
    0.61
     Gleaming
    0.60
    Act Density 0.436%

    No Known Activations