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

    Neuronpedia

    INDEX
    Explanations

    references to thoughts or mental considerations

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to thoughts and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poon
    -0.73
    english
    -0.69
    jong
    -0.66
     Estimates
    -0.66
    ccording
    -0.66
     Policies
    -0.65
     deviations
    -0.63
    aples
    -0.63
    orously
    -0.62
    vision
    -0.62
    POSITIVE LOGITS
     thereof
    0.85
     presented
    0.82
    iest
    0.78
    abl
    0.78
     of
    0.75
    lessness
    0.74
     outwe
    0.72
     afforded
    0.72
    forts
    0.72
     thrill
    0.72
    Act Density 0.199%

    No Known Activations