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

    Neuronpedia

    INDEX
    Explanations

    unique or unusual character sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _svg
    -0.14
     PJ
    -0.14
    iba
    -0.14
    ampie
    -0.13
     Covid
    -0.13
    ustr
    -0.13
    Dlg
    -0.13
     covid
    -0.12
     Cable
    -0.12
     Dra
    -0.12
    POSITIVE LOGITS
     Atomic
    0.38
     atomic
    0.36
    Atomic
    0.34
     store
    0.31
     Store
    0.29
    atomic
    0.29
    _atomic
    0.28
    .Atomic
    0.27
    .atomic
    0.27
     Commit
    0.27
    Act Density 0.002%

    No Known Activations