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

    Neuronpedia

    INDEX
    Explanations

    informal language and conversational phrasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*
    -0.56
    /*++
    -0.42
    makeConstraints
    -0.41
    __':
    -0.40
    uyasha
    -0.39
     nông
    -0.39
    ınt
    -0.39
    vestream
    -0.38
    RuleContext
    -0.38
     AttributeSet
    -0.38
    POSITIVE LOGITS
     right
    2.42
    right
    1.91
    Right
    1.84
     RIGHT
    1.76
     Right
    1.76
    RIGHT
    1.52
     correct
    1.50
     prawda
    1.34
     isn
    1.32
    correct
    1.31
    Act Density 0.337%

    No Known Activations