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

    Neuronpedia

    INDEX
    Explanations

    references to political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "+↵
    -0.15
     PROCUREMENT
    -0.14
    /
    -0.14
    abra
    -0.13
    \"
    -0.13
    buat
    -0.13
     YM
    -0.13
    onder
    -0.13
    lest
    -0.13
    asant
    -0.13
    POSITIVE LOGITS
     [
    0.23
    ...]↵↵
    0.22
    ãĢı↵↵
    0.20
     [...]↵↵
    0.19
     []↵↵
    0.18
     ]↵↵
    0.17
    [s
    0.16
    ...)↵↵
    0.16
    '↵↵
    0.16
    .[
    0.15
    Act Density 0.055%

    No Known Activations