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

    Neuronpedia

    INDEX
    Explanations

    words related to specific names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    substrings indicative of various suffixes or endings in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rampage
    -0.71
     Reincarn
    -0.65
    Initialized
    -0.65
     Vanderbilt
    -0.64
     Juda
    -0.61
     Nept
    -0.61
     RPM
    -0.59
     Pax
    -0.58
     Mankind
    -0.58
    OLOGY
    -0.58
    POSITIVE LOGITS
    anchester
    0.83
    inness
    0.82
    emort
    0.74
    iggs
    0.73
    atform
    0.70
    å°Ĩ
    0.68
    aghan
    0.68
    imately
    0.67
    ances
    0.67
    swick
    0.67
    Act Density 0.218%

    No Known Activations