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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hierarchical structures and organizational categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.67
    addCriterion
    -0.59
    adaptiveStyles
    -0.55
    balleur
    -0.54
     ře
    -0.52
    SourceChecksum
    -0.51
    逅
    -0.50
    MeasureSpec
    -0.50
    LOTTE
    -0.49
    passo
    -0.49
    POSITIVE LOGITS
     himself
    1.03
    himself
    0.85
     his
    0.74
     personally
    0.73
     herself
    0.64
    自身の
    0.61
    自身が
    0.60
     Himself
    0.60
     personalmente
    0.60
     persönlich
    0.57
    Act Density 0.625%

    No Known Activations