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

    Neuronpedia

    INDEX
    Explanations

    names or words with the syllable "kh" followed by specific sequences of letters

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to individuals or entities in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reincarn
    -0.72
    ãĤ¢ãĥ«
    -0.70
    ãĥł
    -0.66
    vironment
    -0.66
    BILITIES
    -0.65
    BIL
    -0.63
    LEASE
    -0.61
    ORTS
    -0.60
    Catal
    -0.59
    ourced
    -0.59
    POSITIVE LOGITS
    obin
    0.90
    awi
    0.86
     Rouge
    0.84
    enei
    0.83
    ®
    0.77
    ouri
    0.73
    azi
    0.72
    abi
    0.70
    nir
    0.69
    istan
    0.69
    Act Density 0.053%

    No Known Activations