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

    Neuronpedia

    INDEX
    Explanations

    expressions of satisfaction or dissatisfaction with something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antlr
    -0.64
    moveToFirst
    -0.61
    yntaxException
    -0.60
    Lore
    -0.59
    [[
    -0.56
     au
    -0.55
    rawDesc
    -0.55
     ged
    -0.54
    ska
    -0.54
     drove
    -0.53
    POSITIVE LOGITS
    atisfactory
    0.98
    satisfaction
    0.90
     satisfaction
    0.90
     satisfactory
    0.89
     disappointment
    0.88
    Satisfaction
    0.88
     satisf
    0.87
     unsatisfactory
    0.85
     disappointments
    0.85
     myſelf
    0.84
    Act Density 0.098%

    No Known Activations