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

    Neuronpedia

    INDEX
    Explanations

    mentions of issues, complaints, and unexpected situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wi
    -0.16
    _CANNOT
    -0.15
    yne
    -0.15
    burgh
    -0.14
    AXB
    -0.14
    oine
    -0.14
    rine
    -0.14
    pel
    -0.14
    º«
    -0.14
    emann
    -0.13
    POSITIVE LOGITS
     sop
    0.16
    ossil
    0.15
     gön
    0.14
     Severity
    0.14
    igel
    0.14
     Wor
    0.14
    onta
    0.14
    intl
    0.14
     minor
    0.13
    umpt
    0.13
    Act Density 0.196%

    No Known Activations