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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "someone" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.77
    DOS
    -0.76
    osterone
    -0.72
    heny
    -0.72
    tnc
    -0.67
    enegger
    -0.65
    aughs
    -0.64
    EngineDebug
    -0.63
    ortex
    -0.63
    interest
    -0.61
    POSITIVE LOGITS
     else
    2.05
    Else
    1.47
    else
    1.34
     Else
    1.31
     who
    1.01
     whose
    0.85
     whom
    0.83
    WithNo
    0.83
     resembling
    0.81
    who
    0.78
    Act Density 0.060%

    No Known Activations