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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ba" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andem
    -0.75
     Attention
    -0.73
    Uncommon
    -0.72
    lessly
    -0.70
    hander
    -0.68
     ancest
    -0.66
    worldly
    -0.65
    starter
    -0.64
    ittal
    -0.62
    ivities
    -0.62
    POSITIVE LOGITS
    ñ
    1.05
    uble
    0.92
    ques
    0.89
    ÅĤ
    0.88
    ibur
    0.88
    bsite
    0.87
    zzle
    0.86
    velength
    0.82
    atar
    0.82
    ffe
    0.81
    Act Density 0.006%

    No Known Activations