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

    Neuronpedia

    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    specific single-letter and multi-letter abbreviations or initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RELE
    -0.71
    é¾įå¥ij士
    -0.71
     Dire
    -0.70
     UP
    -0.67
     MH
    -0.67
     RELEASE
    -0.66
    ãĤ°
    -0.63
     FORM
    -0.63
     Sigma
    -0.63
     Bom
    -0.62
    POSITIVE LOGITS
    immer
    1.21
    abs
    1.11
    orks
    1.10
    arma
    1.05
    ork
    1.03
    oker
    1.02
    arg
    1.00
    ogg
    0.99
    aps
    0.98
    ospital
    0.98
    Act Density 0.104%

    No Known Activations