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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and scientific concepts related to systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.87
    []):
    -0.80
    "")
    -0.78
    )++;
    -0.76
    "):
    -0.76
    '):
    -0.74
    ImageContext
    -0.74
     EconPapers
    -0.73
    ’).
    -0.72
     GenerationType
    -0.71
    POSITIVE LOGITS
    ,
    1.20
    (),
    0.97
    $,
    0.96
     "",
    0.94
    ?,
    0.92
    %,
    0.89
    !,
    0.89
     [],
    0.85
    _,
    0.84
    °,
    0.83
    Act Density 1.150%

    No Known Activations