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

    Neuronpedia

    INDEX
    Explanations

    causal relationships or explanations involving "because."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.76
    Portale
    -0.63
    bootstrapcdn
    -0.59
     extraordinary
    -0.59
    endpush
    -0.58
    brunnen
    -0.53
     الدولى
    -0.51
    basicConfig
    -0.51
    انتهای
    -0.51
    consulté
    -0.50
    POSITIVE LOGITS
     estimés
    0.70
     tartalomajánló
    0.69
    +#+#
    0.63
    ecause
    0.60
    χρι
    0.59
    <bos>
    0.53
    تقاوى
    0.51
     allows
    0.51
     although
    0.51
    دانشنامهٔ
    0.51
    Act Density 0.287%

    No Known Activations