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

    Neuronpedia

    INDEX
    Explanations

    references to fictional elements

    oai_token-act-pair · gpt-3.5-turbo

    references to fictional concepts and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.88
    hammad
    -0.79
    xual
    -0.79
    Da
    -0.77
    ni
    -0.75
    feeding
    -0.74
    cler
    -0.69
    KI
    -0.69
    annis
    -0.68
    hens
    -0.68
    POSITIVE LOGITS
    ized
    1.02
     fictional
    0.93
     universes
    0.90
    acters
    0.89
    istically
    0.86
    ization
    0.84
    izations
    0.83
    ties
    0.82
     recre
    0.82
     portray
    0.81
    Act Density 0.031%

    No Known Activations