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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals, political groups, or specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.77
    ¥µ
    -0.77
    multiple
    -0.70
    ãĤ¦
    -0.70
    izoph
    -0.68
    atorium
    -0.67
    MpServer
    -0.66
    sample
    -0.66
    etheless
    -0.62
    ļéĨĴ
    -0.62
    POSITIVE LOGITS
     fault
    1.22
     who
    0.94
     versus
    0.93
     alone
    0.90
     deciding
    0.88
     vs
    0.86
     doing
    0.83
     Fault
    0.81
     messing
    0.77
     whom
    0.77
    Act Density 0.252%

    No Known Activations