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

    Neuronpedia

    INDEX
    Explanations

    terms related to the programming or coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carthage
    -0.61
    mbia
    -0.59
    enska
    -0.58
    expr
    -0.58
    meia
    -0.58
     Jennings
    -0.56
    hurst
    -0.56
     Felice
    -0.56
    neux
    -0.56
    ridges
    -0.56
    POSITIVE LOGITS
    ot
    3.06
    OT
    2.62
    ots
    2.18
     OT
    1.84
     ot
    1.82
    OTS
    1.75
    Ot
    1.73
     Ot
    1.55
    otan
    1.48
     Sot
    1.48
    Act Density 0.113%

    No Known Activations