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

    Neuronpedia

    INDEX
    Explanations

    tags and attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udes
    -0.19
    erm
    -0.15
    enberg
    -0.14
    pcs
    -0.14
    eres
    -0.14
    arily
    -0.14
    ipple
    -0.14
    orte
    -0.14
    \modules
    -0.14
    eldon
    -0.14
    POSITIVE LOGITS
    alog
    0.18
    alias
    0.18
    ged
    0.17
    dish
    0.16
    ging
    0.16
    åħ±åĴĮ
    0.15
    tone
    0.15
    dro
    0.15
    è·
    0.15
     Rivers
    0.14
    Act Density 0.036%

    No Known Activations