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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions related to time or availability

    oai_token-act-pair · gpt-3.5-turbo

    references to 24-hour time or surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.84
    oslav
    -0.84
    urat
    -0.74
    onyms
    -0.73
    etsk
    -0.72
    onym
    -0.72
    olor
    -0.70
    uras
    -0.69
    achu
    -0.69
    natureconservancy
    -0.67
    POSITIVE LOGITS
    ottest
    0.76
    ailable
    0.73
    PsyNetMessage
    0.70
    hour
    0.68
    ruary
    0.68
    tein
    0.66
    bps
    0.65
    fm
    0.64
    ailability
    0.64
    cision
    0.63
    Act Density 0.188%

    No Known Activations