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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotions and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.17
    agan
    -0.16
    merce
    -0.15
    thur
    -0.15
    agg
    -0.15
     Padding
    -0.14
    nds
    -0.14
    иÑĤоÑĢ
    -0.14
    :
    -0.14
     congen
    -0.14
    POSITIVE LOGITS
    leck
    0.17
    ATAL
    0.15
     vX
    0.15
    adro
    0.15
    IO
    0.14
     ofType
    0.14
    ENDOR
    0.14
    ,retain
    0.14
    LOPT
    0.14
     microtime
    0.14
    Act Density 0.031%

    No Known Activations