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

    Neuronpedia

    INDEX
    Explanations

    syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.15
    zt
    -0.15
    ÂŃi
    -0.15
    ä¸Ī
    -0.15
    chn
    -0.14
    ohl
    -0.14
    sted
    -0.14
    ust
    -0.14
    izz
    -0.14
    ream
    -0.13
    POSITIVE LOGITS
    0.27
    0.17
    0.16
    _SECURE
    0.16
    rips
    0.16
    ãĥ«ãĥķ
    0.15
    0.15
    prav
    0.15
    rava
    0.14
    0.14
    Act Density 0.120%

    No Known Activations