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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating membership or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
    RegressionTest
    -0.66
    initComponents
    -0.61
     GenerationType
    -0.61
     JST
    -0.59
    GOTREF
    -0.59
    AsUp
    -0.58
     callers
    -0.57
     LEYENDO
    -0.57
    achal
    -0.56
    POSITIVE LOGITS
     فريبيس
    0.54
     einer
    0.53
     của
    0.52
     of
    0.51
     subject
    0.50
    PrototypeOf
    0.47
    BeginContext
    0.47
    částí
    0.47
     eines
    0.47
    INCLUDED
    0.46
    Act Density 0.492%

    No Known Activations