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

    Neuronpedia

    INDEX
    Explanations

    single characters in specific sequences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'E' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bleach
    -0.71
    ifiers
    -0.65
     Io
    -0.65
    wagen
    -0.63
    ifiable
    -0.62
     Hayward
    -0.62
     minds
    -0.62
     Anthem
    -0.60
    ãĤ¤ãĥĪ
    -0.59
    ifier
    -0.59
    POSITIVE LOGITS
    LECT
    1.23
    lements
    1.22
    ighty
    1.19
    instein
    1.13
    agle
    1.12
    TERN
    1.11
    ASY
    1.10
    clipse
    1.10
    tymology
    1.09
    ternally
    1.09
    Act Density 0.034%

    No Known Activations