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

    Neuronpedia

    INDEX
    Explanations

    references to data fields and attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owl
    -0.15
    _strcmp
    -0.15
    ops
    -0.14
    çĶ²
    -0.14
    pedia
    -0.14
    åĭĴ
    -0.14
    ι
    -0.14
    osc
    -0.13
    annah
    -0.13
     hlad
    -0.13
    POSITIVE LOGITS
    дап
    0.15
    leftright
    0.14
    -exc
    0.14
     exc
    0.14
    801
    0.13
    adero
    0.13
     Exc
    0.13
    gnore
    0.13
    طاÙĨ
    0.13
    baugh
    0.13
    Act Density 0.022%

    No Known Activations