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

    Neuronpedia

    INDEX
    Explanations

    references to self-identity and personal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lub
    -0.68
     Hof
    -0.63
     Fritz
    -0.63
     pandemonium
    -0.62
     Dull
    -0.62
     Downing
    -0.61
     Aber
    -0.61
     Drunk
    -0.60
     Barney
    -0.59
     Kaz
    -0.59
    POSITIVE LOGITS
     aspire
    1.01
     intend
    0.94
     perceive
    0.79
    abouts
    0.75
     intends
    0.74
    iety
    0.74
    selves
    0.72
     interact
    0.72
     ought
    0.72
     communicate
    0.72
    Act Density 0.074%

    No Known Activations