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

    Neuronpedia

    INDEX
    Explanations

    expressions related to actions and interactions, often highlighting contradictions or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WarningLevel
    -0.56
    FieldNumber
    -0.54
     forKey
    -0.52
    bux
    -0.48
    OGND
    -0.48
     Art
    -0.47
     WARRANT
    -0.46
     art
    -0.45
    vosti
    -0.45
    hObject
    -0.45
    POSITIVE LOGITS
     surla
    0.78
     يتيمه
    0.74
    createClass
    0.60
     prefier
    0.57
    RestTemplate
    0.57
     raiſ
    0.57
     ſtill
    0.54
    RegressionTest
    0.54
    siempre
    0.54
     isolato
    0.54
    Act Density 0.344%

    No Known Activations