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

    Neuronpedia

    INDEX
    Explanations

    questions and references related to identity and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agma
    -0.15
    acente
    -0.15
    bian
    -0.15
    uhan
    -0.14
    θα
    -0.14
    robat
    -0.14
     himself
    -0.14
    ursal
    -0.14
    .TryParse
    -0.14
    .parsers
    -0.14
    POSITIVE LOGITS
     else
    0.43
     exactly
    0.31
     ELSE
    0.29
     Else
    0.27
    else
    0.25
    /how
    0.25
     among
    0.23
     amongst
    0.23
    _else
    0.23
    	else
    0.22
    Act Density 0.037%

    No Known Activations