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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey evaluation or judgment about people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saveiro
    -0.64
     dilatation
    -0.64
    lorette
    -0.63
     extradition
    -0.62
     atheism
    -0.61
     ModelExpression
    -0.61
     Sancho
    -0.60
     Baptists
    -0.60
     pector
    -0.60
    örté
    -0.60
    POSITIVE LOGITS
     “
    0.91
     a
    0.82
     "
    0.78
     ‘
    0.73
     truly
    0.71
     an
    0.69
     „
    0.62
     «
    0.60
     '
    0.59
     being
    0.58
    Act Density 0.425%

    No Known Activations