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

    Neuronpedia

    INDEX
    Explanations

    words related to ambiguity and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.16
    gil
    -0.15
    bach
    -0.15
    hiba
    -0.15
    LK
    -0.15
    irit
    -0.14
    .NewLine
    -0.14
    afa
    -0.14
     convention
    -0.14
    Unload
    -0.14
    POSITIVE LOGITS
    ATUS
    0.16
    /cache
    0.15
    ("'"
    0.15
    èį£
    0.14
    uder
    0.14
     Sting
    0.14
     Rank
    0.14
     Pier
    0.14
    -tm
    0.14
     cab
    0.14
    Act Density 0.118%

    No Known Activations