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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters used in text, especially arrow symbols denoting actions or directions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.77
     scatter
    -0.70
     rooting
    -0.70
    lda
    -0.67
     downed
    -0.66
     staggered
    -0.65
    ctors
    -0.65
     swept
    -0.64
     wind
    -0.63
     detached
    -0.62
    POSITIVE LOGITS
    £
    1.12
    į
    1.05
    ¹
    1.04
    º
    1.03
    »
    0.99
    ¿
    0.98
    ĸļ
    0.95
    âĸº
    0.93
    âĢł
    0.93
    ¯
    0.92
    Act Density 0.566%

    No Known Activations