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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experience and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    הערות
    -0.61
    MMV
    -0.60
    expandindo
    -0.59
     Hast
    -0.48
    amazonaws
    -0.48
    :");
    -0.47
    ANCO
    -0.47
    ？】
    -0.46
    '],
    -0.46
    ésia
    -0.46
    POSITIVE LOGITS
     Tierney
    0.62
     dumne
    0.61
     بيها
    0.60
    ◄
    0.57
     bellows
    0.55
     bouteille
    0.55
     voyons
    0.55
     thorium
    0.55
     Wages
    0.55
    RuleContext
    0.55
    Act Density 0.091%

    No Known Activations