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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical processes and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     was
    -0.44
     Cæsar
    -0.44
    을
    -0.43
     intangible
    -0.42
    liminaries
    -0.41
    intenant
    -0.41
     auffi
    -0.41
     silang
    -0.41
    <bos>
    -0.40
    SCAPE
    -0.40
    POSITIVE LOGITS
     ist
    0.92
     hat
    0.83
    دانشنامهٔ
    0.75
     sind
    0.74
     виправивши
    0.73
    RenderAtEndOf
    0.72
     wird
    0.71
     gilt
    0.70
     tut
    0.70
     kann
    0.69
    Act Density 0.058%

    No Known Activations