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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly slashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ification
    -0.67
     Survivors
    -0.65
    idious
    -0.65
    born
    -0.64
     Toys
    -0.63
     amen
    -0.63
    eren
    -0.62
     Wend
    -0.61
    usky
    -0.61
     loyal
    -0.60
    POSITIVE LOGITS
    /.
    1.11
     (.
    0.96
    wcsstore
    0.91
    olitics
    0.89
    _.
    0.88
    lihood
    0.88
    adish
    0.87
    vernment
    0.86
     ~/.
    0.85
    OPLE
    0.84
    Act Density 0.012%

    No Known Activations