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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and self-descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    هد
    -0.53
     هد
    -0.49
     تق
    -0.44
     INVENTION
    -0.44
     suav
    -0.43
    Quy
    -0.43
     Cabe
    -0.43
    調
    -0.42
    renos
    -0.41
     Encu
    -0.41
    POSITIVE LOGITS
     Efq
    0.92
    TagMode
    0.79
    ReusableCell
    0.78
    Portale
    0.77
     ſch
    0.76
     whiteColor
    0.75
     مواليد
    0.75
    awakeFromNib
    0.73
     Jefus
    0.72
    owohl
    0.72
    Act Density 0.206%

    No Known Activations