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

    Neuronpedia

    INDEX
    Explanations

    references to qualitative assessments of positive and negative attributes or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onItemClick
    -0.68
    thschild
    -0.64
    __*/
    -0.62
    }{*}{}
    -0.61
    rboles
    -0.59
     acaso
    -0.57
    Hutch
    -0.55
     عج
    -0.55
    brigens
    -0.55
    illots
    -0.55
    POSITIVE LOGITS
     Posi
    1.22
    PositiveButton
    1.16
     negatives
    1.12
     POSITIVE
    1.12
     positives
    1.11
     (+)
    1.09
    POSITIVE
    1.08
    Positives
    1.02
     positiv
    1.00
     Neg
    0.96
    Act Density 0.108%

    No Known Activations