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

    Neuronpedia

    INDEX
    Explanations

    instances of sudden unexpected events or changes

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lier
    -0.62
    NAS
    -0.60
     entry
    -0.59
     HMS
    -0.59
    forth
    -0.59
    sylvania
    -0.58
    nown
    -0.57
    NRS
    -0.56
    ATURES
    -0.56
    EMA
    -0.56
    POSITIVE LOGITS
     sudden
    0.85
     dozen
    0.81
     bunch
    0.78
     hundred
    0.75
    ught
    0.75
     handful
    0.73
    dozen
    0.71
     lot
    0.69
     tremend
    0.68
     few
    0.68
    Act Density 0.108%

    No Known Activations