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

    Neuronpedia

    INDEX
    Explanations

    components related to code structure and control flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indow
    -0.19
    izoph
    -0.16
    ultz
    -0.15
    йн
    -0.15
    ldr
    -0.15
    lero
    -0.15
     Cord
    -0.15
    elman
    -0.14
    imir
    -0.14
    ammer
    -0.14
    POSITIVE LOGITS
     until
    0.37
     while
    0.35
    _until
    0.32
    until
    0.31
     Until
    0.30
    _while
    0.29
    while
    0.29
     WHILE
    0.28
    Until
    0.28
     While
    0.28
    Act Density 0.187%

    No Known Activations