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

    Neuronpedia

    INDEX
    Explanations

    references to hyper conditions or hyperactivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.60
    c
    -0.54
    <eos>
    -0.53
    -
    -0.50
    ’
    -0.49
    ca
    -0.49
    nd
    -0.49
    &
    -0.49
    a
    -0.48
    w
    -0.47
    POSITIVE LOGITS
    UnusedPrivate
    1.04
     saites
    1.02
     imprimée
    0.99
    PreferredItem
    0.89
     Credentials
    0.88
     fabricate
    0.86
    Parcelize
    0.84
     للمعارف
    0.83
    ﷺ
    0.83
     &___
    0.83
    Act Density 0.358%

    No Known Activations