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

    Neuronpedia

    INDEX
    Explanations

    words related to a particular language or script with a unique character set

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ength
    -0.90
    acea
    -0.88
    oaded
    -0.86
    arios
    -0.81
    istically
    -0.81
    ient
    -0.80
    anguage
    -0.79
    adium
    -0.78
    pmwiki
    -0.78
    uality
    -0.78
    POSITIVE LOGITS
    м
    1.21
    ·
    1.18
    н
    1.09
    д
    1.05
    Ð
    1.04
    в
    1.03
    л
    1.02
    ÑĢ
    1.02
    к
    1.01
    Ĺ
    0.98
    Act Density 0.015%

    No Known Activations