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

    Neuronpedia

    INDEX
    Explanations

    verbs related to successful or impressive actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urnal
    -0.68
    esa
    -0.67
    etary
    -0.65
    cius
    -0.63
    PET
    -0.61
    hedral
    -0.58
     Ore
    -0.57
    ibus
    -0.56
    endium
    -0.56
     morning
    -0.56
    POSITIVE LOGITS
    fitted
    0.78
    lier
    0.78
    casts
    0.77
    last
    0.77
    stretched
    0.76
    doing
    0.75
    fitting
    0.74
    \\\\\\\\
    0.73
     linebacker
    0.72
     Burnett
    0.71
    Act Density 0.061%

    No Known Activations