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

    Neuronpedia

    INDEX
    Explanations

    terms related to spatial metrics and storage requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.80
     Efq
    -0.77
     مشين
    -0.73
    RegressionTest
    -0.70
     Houſe
    -0.69
     Majefty
    -0.68
     Cæsar
    -0.68
     Monfieur
    -0.66
     ―――――
    -0.64
     Theſe
    -0.63
    POSITIVE LOGITS
     space
    1.29
    space
    1.03
     SPACE
    1.02
     Space
    0.99
    Space
    0.98
    SPACE
    0.94
     espacio
    0.92
     espaço
    0.88
     spaces
    0.84
     espace
    0.84
    Act Density 0.341%

    No Known Activations