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

    Neuronpedia

    INDEX
    Explanations

    names of countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    adjectives related to qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯ãĥ³
    -0.88
    EEK
    -0.81
    CHA
    -0.81
    olkien
    -0.77
    lished
    -0.76
     Kraken
    -0.75
    Oracle
    -0.74
    urai
    -0.74
    URA
    -0.72
    Kids
    -0.72
    POSITIVE LOGITS
    ysis
    1.13
    ity
    0.96
    ial
    0.89
    ogue
    0.83
    pha
    0.82
    ially
    0.80
    abolic
    0.80
    tarian
    0.78
    ikes
    0.76
    tarians
    0.76
    Act Density 0.013%

    No Known Activations