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

    Neuronpedia

    INDEX
    Explanations

    causal relationships and justifications in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rub
    -0.45
    كويكب
    -0.45
     BoxFit
    -0.43
     للمعارف
    -0.41
    rub
    -0.38
     sterling
    -0.36
     Burgh
    -0.35
    ajs
    -0.35
     wrapping
    -0.35
     rubbing
    -0.35
    POSITIVE LOGITS
    AndEndTag
    0.65
    makeConstraints
    0.57
     Paglinawan
    0.51
    ViewFeatures
    0.47
     sababu
    0.45
    adaptiveStyles
    0.45
    reason
    0.45
    orElseThrow
    0.44
    posedge
    0.44
     because
    0.44
    Act Density 1.020%

    No Known Activations