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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment and positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ียà¸Ķ
    -0.15
     individ
    -0.14
     seins
    -0.14
     Injector
    -0.14
    AndGet
    -0.14
    ahren
    -0.13
    ocol
    -0.13
    avana
    -0.13
     $#
    -0.13
    ipop
    -0.13
    POSITIVE LOGITS
    ayi
    0.16
     somehow
    0.15
     treff
    0.14
     escap
    0.14
    VERR
    0.14
     satisfaction
    0.14
     nÃło
    0.14
    Ñħи
    0.13
    able
    0.13
    bsolute
    0.13
    Act Density 0.007%

    No Known Activations