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

    Neuronpedia

    INDEX
    Explanations

    elements and structures related to code or programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DBG
    -0.17
    esi
    -0.15
    YRO
    -0.14
    ovah
    -0.14
    809
    -0.14
    klad
    -0.14
    808
    -0.13
    rote
    -0.13
    batim
    -0.13
    yro
    -0.13
    POSITIVE LOGITS
     rules
    0.26
     pattern
    0.23
    Rules
    0.23
    rules
    0.22
     Pattern
    0.22
     Rules
    0.21
    _rules
    0.21
    rule
    0.21
     rule
    0.21
    .validators
    0.20
    Act Density 0.098%

    No Known Activations