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

    Neuronpedia

    INDEX
    Explanations

    references to actions and conditions related to presence and absence, particularly in legal or environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emale
    -0.18
    eman
    -0.16
    empor
    -0.15
    arkin
    -0.15
    ázi
    -0.15
    synthesize
    -0.15
    ↵↵
    -0.14
    ercial
    -0.14
    evin
    -0.14
    apo
    -0.14
    POSITIVE LOGITS
    ssa
    0.16
    ux
    0.15
    iffer
    0.15
     TAM
    0.15
     faction
    0.14
    CREMENT
    0.14
     Schneider
    0.14
    IGNORE
    0.14
    /embed
    0.14
     tam
    0.14
    Act Density 0.060%

    No Known Activations