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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or inclination towards actions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ResourceBundle
    -0.59
    seur
    -0.57
    invokeLater
    -0.56
    upta
    -0.55
    pub
    -0.53
    haya
    -0.53
    intera
    -0.52
    seurs
    -0.52
     Daily
    -0.51
    wald
    -0.51
    POSITIVE LOGITS
    +#+#
    0.80
    évaluateur
    0.76
    homonymie
    0.70
     EconPapers
    0.68
    Diweddarwch
    0.67
    SerializedSize
    0.66
     comigo
    0.65
     prefi
    0.64
    empio
    0.63
     vais
    0.61
    Act Density 0.053%

    No Known Activations