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

    Neuronpedia

    INDEX
    Explanations

    mentions of routine activities or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Garth
    -0.74
    Garth
    -0.71
     BUILD
    -0.68
    theless
    -0.65
    etah
    -0.62
     eget
    -0.61
    nachweis
    -0.61
    Heal
    -0.61
    Maar
    -0.61
    alc
    -0.59
    POSITIVE LOGITS
     Routine
    0.97
    ROUTINE
    0.91
     routine
    0.90
    Routine
    0.89
    routine
    0.87
     onAnimation
    0.87
    ServletException
    0.87
    Kong
    0.87
     OMITBAD
    0.85
     Kong
    0.85
    Act Density 0.088%

    No Known Activations