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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific fictional location or character

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'E'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kenobi
    -0.73
     Anthem
    -0.70
    wagen
    -0.64
     Bleach
    -0.63
     Showdown
    -0.63
    ãĤ¤ãĥĪ
    -0.63
     Akira
    -0.62
     Kitchen
    -0.61
     juggling
    -0.61
     Rebels
    -0.61
    POSITIVE LOGITS
    ASY
    1.12
    AST
    1.09
    nerg
    1.08
    fficient
    1.08
    ighty
    1.07
    rect
    1.06
    tymology
    1.03
    isner
    1.03
    ves
    1.02
    lev
    1.01
    Act Density 0.030%

    No Known Activations