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

    Neuronpedia

    INDEX
    Explanations

    mentions of creators or authors

    oai_token-act-pair · gpt-3.5-turbo

    references to creators or authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abb
    -0.79
    olit
    -0.70
    etta
    -0.68
     Spa
    -0.67
    ishops
    -0.66
    ALE
    -0.65
     Dates
    -0.65
    oles
    -0.64
     Clin
    -0.64
    late
    -0.63
    POSITIVE LOGITS
     creator
    1.27
    creator
    1.20
     creators
    1.12
     creat
    0.94
     inventor
    0.90
    ãĥķãĤ¡
    0.88
    caster
    0.87
     laureate
    0.84
     extraord
    0.83
    ãĥĨãĤ£
    0.82
    Act Density 0.007%

    No Known Activations