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

    Neuronpedia

    INDEX
    Explanations

    statements and reports involving personal admissions and denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.59
    RenderAtEndOf
    -0.59
    참고
    -0.58
    ممنون
    -0.56
    KommentareTeilen
    -0.56
     eorum
    -0.55
     normaux
    -0.55
     détru
    -0.54
     virtud
    -0.54
     exécut
    -0.54
    POSITIVE LOGITS
     announced
    0.82
     announcing
    0.79
     publicly
    0.78
     announcement
    0.74
     announce
    0.73
     anuncio
    0.67
     announcements
    0.67
     hinted
    0.64
     tweeted
    0.62
     stated
    0.61
    Act Density 0.292%

    No Known Activations