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

    Neuronpedia

    INDEX
    Explanations

    references to symbols and symbolism in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avors
    -0.19
    aus
    -0.18
    liness
    -0.17
    iba
    -0.17
    est
    -0.16
    elow
    -0.16
    eenth
    -0.16
    STA
    -0.15
    SPAN
    -0.15
    ÑĢави
    -0.15
    POSITIVE LOGITS
    ically
    0.35
    ical
    0.26
    izes
    0.26
    ize
    0.23
    izing
    0.22
    ized
    0.21
    isms
    0.21
    lic
    0.21
    lico
    0.20
    atically
    0.20
    Act Density 0.016%

    No Known Activations