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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and method signatures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atar
    -0.16
     Caller
    -0.16
    izo
    -0.15
     çķ
    -0.15
    acom
    -0.15
    isco
    -0.15
    irsch
    -0.14
    RET
    -0.14
    ikki
    -0.14
    acus
    -0.14
    POSITIVE LOGITS
     existing
    0.23
    (existing
    0.22
     Existing
    0.19
    existing
    0.19
    Existing
    0.17
    -existing
    0.16
    exists
    0.15
    796
    0.15
    ters
    0.15
     editable
    0.15
    Act Density 0.228%

    No Known Activations