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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lockout
    -0.71
     nutshell
    -0.66
     throne
    -0.65
     clipboard
    -0.65
    士
    -0.65
     awhile
    -0.64
    raints
    -0.63
    ©¶æ
    -0.63
    è¦ļéĨĴ
    -0.63
     similar
    -0.62
    POSITIVE LOGITS
    wise
    0.69
    udos
    0.69
    aila
    0.67
    pecially
    0.67
    anta
    0.64
    iola
    0.63
    dra
    0.63
    atis
    0.63
    conn
    0.62
    added
    0.61
    Act Density 0.431%

    No Known Activations