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

    Neuronpedia

    INDEX
    Explanations

    numerical data or references in a scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    82
    -0.16
    .Widget
    -0.15
    pre
    -0.15
    867
    -0.14
    91
    -0.14
     recently
    -0.14
     sustain
    -0.14
    83
    -0.14
    re
    -0.13
    c
    -0.13
    POSITIVE LOGITS
    101
    0.41
    109
    0.32
    100
    0.31
    108
    0.29
    110
    0.29
    111
    0.28
    103
    0.27
    338
    0.27
    339
    0.27
    117
    0.25
    Act Density 0.010%

    No Known Activations