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

    Neuronpedia

    INDEX
    Explanations

    negative comparisons or worse experiences relative to others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.69
    +:+
    -0.61
     MainAxisSize
    -0.55
    StoryboardSegue
    -0.55
     beginnetje
    -0.53
    بوابة
    -0.52
     оригіналу
    -0.50
     مشين
    -0.50
    randrange
    -0.50
    ;");
    -0.50
    POSITIVE LOGITS
     surpassing
    0.75
     superior
    0.74
     surpassed
    0.71
     surpasses
    0.68
     superiority
    0.65
     surpass
    0.64
    ViewFeatures
    0.61
    superior
    0.61
     comparison
    0.60
    EDEFAULT
    0.60
    Act Density 0.286%

    No Known Activations