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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.75
    tanleria
    -0.72
    Hentet
    -0.68
    rawDesc
    -0.65
    PerformLayout
    -0.65
    GIVEREF
    -0.64
     kaarangay
    -0.64
    iastes
    -0.63
    BibitemShut
    -0.63
     ModelExpression
    -0.63
    POSITIVE LOGITS
    bar
    0.45
    uk
    0.44
    ent
    0.44
    bu
    0.43
    AppMethodBeat
    0.43
     protagonistas
    0.42
     usually
    0.42
    diali
    0.42
    an
    0.42
     sav
    0.42
    Act Density 0.205%

    No Known Activations