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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures or phrases that indicate relationships and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     հղումներ
    -0.51
    verifyException
    -0.46
    ThroughAttribute
    -0.45
     iconLine
    -0.42
    Odkazy
    -0.40
     referrerpolicy
    -0.40
    __":
    -0.40
    ChildScrollView
    -0.40
     препратки
    -0.40
     חיצוניים
    -0.40
    POSITIVE LOGITS
    being
    0.45
    say
    0.43
    been
    0.43
     Like
    0.43
    EDEFAULT
    0.42
    rule
    0.42
    facts
    0.42
     Same
    0.42
    raison
    0.41
     beho
    0.41
    Act Density 0.826%

    No Known Activations