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

    Neuronpedia

    INDEX
    Explanations

    the concept of a 'two' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icipated
    -0.66
    lance
    -0.65
    OTOS
    -0.63
    ushima
    -0.62
    raints
    -0.61
     Caption
    -0.60
     relevance
    -0.60
     Worldwide
    -0.60
    ifacts
    -0.59
    yles
    -0.59
    POSITIVE LOGITS
    fold
    0.89
    quel
    0.86
    peat
    0.79
    teenth
    0.76
     dimensional
    0.73
    acious
    0.70
    legged
    0.69
    aciously
    0.68
    dimensional
    0.65
    plus
    0.64
    Act Density 0.102%

    No Known Activations