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

    Neuronpedia

    INDEX
    Explanations

    certain non-Latin characters, possibly related to a specific language or text encoding

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieve
    -0.72
    ierrez
    -0.70
    reet
    -0.67
     Heights
    -0.67
     Boll
    -0.66
    oppable
    -0.66
     Bronx
    -0.64
    leeve
    -0.64
     Kham
    -0.63
     Rosenberg
    -0.63
    POSITIVE LOGITS
    ħĭ
    0.94
    voc
    0.89
    vention
    0.84
    lege
    0.83
    ĻĤ
    0.83
    technology
    0.79
    Age
    0.76
    jection
    0.75
    tains
    0.74
    Ĥª
    0.74
    Act Density 0.031%

    No Known Activations