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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news or media reports

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to news or updates on events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antics
    -0.67
    Stew
    -0.65
    ternity
    -0.60
    sed
    -0.59
    asper
    -0.58
     Eag
    -0.57
    ucky
    -0.57
     territ
    -0.57
     manslaughter
    -0.57
    hens
    -0.55
    POSITIVE LOGITS
     alleging
    0.90
     indicate
    0.84
     circulating
    0.84
     quoting
    0.84
     indicating
    0.83
     circulated
    0.83
     citing
    0.82
     suggesting
    0.81
     surfaced
    0.81
     corrobor
    0.79
    Act Density 0.073%

    No Known Activations