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

    Neuronpedia

    INDEX
    Explanations

    key terms and concepts associated with communication and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fte
    -0.07
     Heller
    -0.06
    bra
    -0.06
    ê³¼ìĿĺ
    -0.06
    cko
    -0.06
    еÑĦ
    -0.06
    lier
    -0.06
    lein
    -0.06
    rst
    -0.06
    upe
    -0.06
    POSITIVE LOGITS
    _ASSUME
    0.07
     identified
    0.07
    .sessions
    0.07
    èĥĨ
    0.07
     boobs
    0.07
    identified
    0.07
    é¼ĵ
    0.07
    -Identifier
    0.07
    kills
    0.06
     effective
    0.06
    Act Density 0.000%

    No Known Activations