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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to opinions and subjective evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     feature
    -0.49
    Feature
    -0.47
    bewerken
    -0.47
     pomen
    -0.47
     risol
    -0.47
    feature
    -0.46
     Feature
    -0.44
     dedicate
    -0.44
    گی
    -0.43
    ym
    -0.42
    POSITIVE LOGITS
     formed
    0.77
    setVerticalGroup
    0.77
     expressed
    0.76
    expressed
    0.75
     Formed
    0.73
    WithIOException
    0.71
    InjectAttribute
    0.70
    addCriterion
    0.70
     BASED
    0.68
     ModelExpression
    0.65
    Act Density 0.368%

    No Known Activations