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

    Neuronpedia

    INDEX
    Explanations

    concepts related to values, beliefs, and their implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     σύ
    -0.51
     "
    -0.50
    atoi
    -0.49
    RequestParam
    -0.48
     «
    -0.47
     “
    -0.45
    oporosis
    -0.44
    iennes
    -0.44
    まし
    -0.44
     Loh
    -0.43
    POSITIVE LOGITS
     المعيارى
    0.86
    DockStyle
    0.78
     ་་
    0.73
     Theſe
    0.73
     للمعارف
    0.73
    ſelves
    0.72
     greateſt
    0.72
    ConstraintMaker
    0.68
     Houſe
    0.68
     itſelf
    0.68
    Act Density 0.354%

    No Known Activations