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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotions and personal dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umper
    -0.15
    871
    -0.15
    RuleContext
    -0.15
    756
    -0.15
    rael
    -0.15
    690
    -0.15
    adiens
    -0.15
    bou
    -0.14
     styl
    -0.14
    095
    -0.14
    POSITIVE LOGITS
     equipments
    0.14
    [P
    0.14
     gay
    0.14
    ιά
    0.14
     gen
    0.14
     muc
    0.14
     HQ
    0.14
    obus
    0.13
     babel
    0.13
     zest
    0.13
    Act Density 0.322%

    No Known Activations