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

    Neuronpedia

    INDEX
    Explanations

    discussions that express feelings and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imdi
    -0.15
    ãģķãĤĵãģ¯
    -0.15
    cctor
    -0.15
    çĶ³åįļ
    -0.15
    icularly
    -0.14
     à¸ģรà¸ģ
    -0.14
    taboola
    -0.14
    _CSR
    -0.14
    Normalization
    -0.14
    opus
    -0.14
    POSITIVE LOGITS
     there
    0.27
     if
    0.26
     it
    0.23
     when
    0.23
     after
    0.23
     while
    0.23
     this
    0.22
     for
    0.22
     as
    0.22
     we
    0.21
    Act Density 0.281%

    No Known Activations