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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional states and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usterity
    -0.16
    uzzi
    -0.15
    abo
    -0.15
    òn
    -0.14
     Feeling
    -0.14
    åģ¥
    -0.14
    estatus
    -0.14
     tá»ı
    -0.14
    .Std
    -0.14
    essen
    -0.14
    POSITIVE LOGITS
     like
    0.30
     compelled
    0.27
     obligated
    0.24
     strongly
    0.23
     obliged
    0.23
     guilty
    0.21
     pressure
    0.20
     nhÆ°
    0.20
    -good
    0.19
     comfortable
    0.19
    Act Density 0.046%

    No Known Activations