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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    FontOfSize
    -0.60
    adaş
    -0.60
     baud
    -0.60
     Beres
    -0.60
    setof
    -0.59
     Bird
    -0.59
    ('/:
    -0.59
     Hawkins
    -0.58
     AppDelegate
    -0.57
    oiseau
    -0.56
    POSITIVE LOGITS
    VersionUID
    0.69
     endwhile
    0.69
     للمعارف
    0.63
     verfü
    0.59
     defaultstate
    0.58
     quæ
    0.57
    ]})
    0.57
    quine
    0.56
    inį
    0.55
     ComVisible
    0.54
    Act Density 0.004%

    No Known Activations