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

    Neuronpedia

    INDEX
    Explanations

    references to significant concepts or events in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -between
    -0.18
    front
    -0.17
     Plus
    -0.16
    stad
    -0.15
    ico
    -0.15
    /from
    -0.15
    à¸į
    -0.14
     Genuine
    -0.14
    oca
    -0.14
    Plus
    -0.14
    POSITIVE LOGITS
     fact
    0.39
     effect
    0.35
     essence
    0.35
     part
    0.31
     itself
    0.28
     turn
    0.28
     truth
    0.28
     large
    0.27
     principle
    0.26
     theory
    0.26
    Act Density 0.222%

    No Known Activations