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

    Neuronpedia

    INDEX
    Explanations

    references to roles and responsibilities in a professional setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.23
     ‘
    -0.21
     («
    -0.21
     ("
    -0.20
     (`
    -0.20
    []"
    -0.19
     "[
    -0.18
    ."[
    -0.18
     —
    -0.18
     (!
    -0.18
    POSITIVE LOGITS
    --↵
    0.38
    -↵
    0.33
     uh
    0.26
     kind
    0.24
     sort
    0.24
    --↵↵
    0.24
    --,
    0.23
    --
    0.22
     um
    0.22
     --↵
    0.22
    Act Density 0.674%

    No Known Activations