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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific emotions or states of feeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -0.84
     itſelf
    -0.83
    ſelf
    -0.82
     {},
    -0.79
     houſe
    -0.78
     Reſ
    -0.77
     ſche
    -0.77
     Houſe
    -0.77
     Anſ
    -0.77
     ſy
    -0.75
    POSITIVE LOGITS
     مواليد
    0.55
     G
    0.53
     T
    0.52
     C
    0.52
     I
    0.49
    hen
    0.48
    ětí
    0.47
    ModelSerializer
    0.46
    StoryboardSegue
    0.45
     my
    0.45
    Act Density 0.208%

    No Known Activations