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

    Neuronpedia

    INDEX
    Explanations

    syntactic punctuation and structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egment
    -0.16
    lush
    -0.16
    igure
    -0.15
    lap
    -0.15
     Practical
    -0.14
     prov
    -0.14
    ignum
    -0.14
     blind
    -0.14
    ennen
    -0.13
     Cheney
    -0.13
    POSITIVE LOGITS
     case
    0.28
    case
    0.25
     Case
    0.20
     cases
    0.20
    Case
    0.20
    .case
    0.20
     caso
    0.19
    -case
    0.19
    _case
    0.18
    (case
    0.18
    Act Density 0.028%

    No Known Activations