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

    Neuronpedia

    INDEX
    Explanations

    discussions about perception and interpretation of reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avra
    -0.20
    ante
    -0.15
    chk
    -0.15
    efa
    -0.15
    Denied
    -0.15
     Sherman
    -0.15
    elmet
    -0.15
    onto
    -0.14
    hta
    -0.14
    ANTE
    -0.14
    POSITIVE LOGITS
     differently
    0.30
     sebagai
    0.19
     jako
    0.17
     unfavor
    0.15
    ä½ľä¸º
    0.15
     ë°ĶëĿ¼
    0.15
    /gpl
    0.15
     as
    0.14
    ials
    0.14
     hol
    0.14
    Act Density 0.111%

    No Known Activations