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

    Neuronpedia

    INDEX
    Explanations

    specific names, likely related to characters or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to characters and places, particularly in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tering
    -0.83
     Cumber
    -0.75
    zman
    -0.72
    eers
    -0.68
     Manip
    -0.67
    enburg
    -0.67
     Wonderland
    -0.64
    zel
    -0.64
     inval
    -0.64
     Box
    -0.64
    POSITIVE LOGITS
    phia
    0.95
    ourse
    0.81
    prise
    0.75
    icago
    0.72
    prises
    0.71
    ĺħ
    0.70
    roots
    0.69
    WP
    0.69
     Trace
    0.68
    dain
    0.68
    Act Density 0.065%

    No Known Activations