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

    Neuronpedia

    INDEX
    Explanations

    terms related to gender norms and communication in community contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.85
     externi
    -0.73
    Jereo
    -0.67
    évaluateur
    -0.64
    helial
    -0.63
    +#+#
    -0.62
    withstanding
    -0.62
     esternos
    -0.62
    不及
    -0.61
    COLLE
    -0.61
    POSITIVE LOGITS
     Malk
    0.68
    urn
    0.68
    PreferredItem
    0.61
    ark
    0.60
    transQ
    0.59
    ORN
    0.57
     Erm
    0.56
     Tark
    0.56
     Torn
    0.56
    arn
    0.56
    Act Density 0.511%

    No Known Activations