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

    Neuronpedia

    INDEX
    Explanations

    sequences of alphanumeric characters and words associated with code or data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.67
     汉
    -0.53
    áját
    -0.50
    Statut
    -0.48
    StringValue
    -0.47
    reactstrap
    -0.46
     fav
    -0.46
    RegressionTest
    -0.46
     ‘
    -0.45
    :+:
    -0.44
    POSITIVE LOGITS
     bezeichneter
    0.73
     ―――――
    0.71
     باخ
    0.69
     quæ
    0.66
     Efq
    0.66
     Allegretto
    0.64
     ويكيميديا
    0.62
    lisle
    0.62
    rzost
    0.62
     $_(
    0.61
    Act Density 0.412%

    No Known Activations