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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables in the context of scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utives
    -0.34
     Leading
    -0.34
    Leading
    -0.32
     kaarangay
    -0.32
    Calling
    -0.31
     Call
    -0.30
    łaj
    -0.29
     llamaba
    -0.29
     leading
    -0.29
    Call
    -0.28
    POSITIVE LOGITS
     للمعارف
    0.68
     يتيمه
    0.63
    colgante
    0.56
    DockStyle
    0.56
    iſchen
    0.54
     GenerationType
    0.52
    CloseOperation
    0.51
     nemmeno
    0.50
     pungkas
    0.49
    المناصب
    0.49
    Act Density 0.461%

    No Known Activations