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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    principalTable
    -0.91
     slutt
    -0.87
     '\\;'
    -0.83
     henvis
    -0.81
     feroit
    -0.80
    +#+
    -0.79
    +#+#
    -0.78
     thermique
    -0.78
    fromnode
    -0.77
    LabelTagHelper
    -0.77
    POSITIVE LOGITS
     g
    0.47
     post
    0.45
    serviceWorker
    0.44
     pass
    0.44
     dos
    0.44
     s
    0.42
     Covid
    0.42
     nog
    0.40
     Do
    0.39
     Pass
    0.39
    Act Density 0.010%

    No Known Activations