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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive and negative evaluations or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.71
    illots
    -0.69
     CreateTagHelper
    -0.68
     onItemClick
    -0.68
    rboles
    -0.66
     AspNetCore
    -0.66
     cuánt
    -0.64
    thschild
    -0.64
    fvar
    -0.63
     Numerology
    -0.62
    POSITIVE LOGITS
     Posi
    1.33
    PositiveButton
    1.28
     positives
    1.22
     POSITIVE
    1.19
    Positives
    1.14
    POSITIVE
    1.14
     (+)
    1.13
     positiv
    1.13
     positive
    1.08
    Positive
    1.08
    Act Density 0.121%

    No Known Activations