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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating deviations from the norm or traditional expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åºķ
    -0.17
    /
    -0.14
     nobody
    -0.14
    estar
    -0.14
     Already
    -0.14
     bor
    -0.13
    blr
    -0.13
    rain
    -0.13
    :
    -0.13
    IPC
    -0.13
    POSITIVE LOGITS
     typical
    0.38
     usual
    0.38
    usual
    0.32
    typ
    0.27
     previous
    0.25
     typically
    0.25
     other
    0.24
     Typical
    0.23
    éĢļ常
    0.23
    previous
    0.23
    Act Density 0.129%

    No Known Activations