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

    Neuronpedia

    INDEX
    Explanations

    references to default configurations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typical
    -0.54
    featureID
    -0.54
     usual
    -0.53
    principalTable
    -0.51
     standard
    -0.50
    RemoveField
    -0.48
     standards
    -0.44
    Autoritní
    -0.43
     familiar
    -0.43
     createSlice
    -0.41
    POSITIVE LOGITS
     Standard
    1.09
     Default
    0.96
    Standard
    0.93
    Default
    0.90
     Simple
    0.85
    Simple
    0.76
     Normal
    0.72
    Normal
    0.67
     Std
    0.60
    Std
    0.57
    Act Density 0.154%

    No Known Activations