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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to documents or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUND
    -0.15
    ì§ģ
    -0.14
     knot
    -0.14
    .libs
    -0.13
    ylon
    -0.13
    efa
    -0.13
    abled
    -0.13
     Äįin
    -0.13
    .attrs
    -0.12
     hra
    -0.12
    POSITIVE LOGITS
    ÃĹ↵↵
    0.15
     Haz
    0.14
     Koch
    0.14
    ambiguous
    0.14
     guarded
    0.14
    yna
    0.14
    ires
    0.13
    Haz
    0.13
    rated
    0.13
     artillery
    0.13
    Act Density 0.047%

    No Known Activations