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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance and success

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    achen
    -0.59
     good
    -0.59
    '</
    -0.59
    ')")
    -0.59
    "</
    -0.57
     Lenz
    -0.57
     Apre
    -0.57
     puro
    -0.56
     Lanz
    -0.56
    UNTAIN
    -0.56
    POSITIVE LOGITS
    eraard
    0.77
     ModelExpression
    0.71
     obicei
    0.69
    addComponent
    0.66
     esternos
    0.66
    évaluateur
    0.65
    findpost
    0.64
    rungsseite
    0.63
     الرياضيه
    0.63
    ivably
    0.63
    Act Density 0.020%

    No Known Activations