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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns or names in sentences indicating some form of action or behavior

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.94
    anwhile
    -0.85
    ãĥ¼ãĥĨ
    -0.80
    ģĸ
    -0.77
    FORMATION
    -0.74
    è¦ļéĨĴ
    -0.74
    WAYS
    -0.71
    ħĭ
    -0.69
     separatist
    -0.68
     Carbuncle
    -0.66
    POSITIVE LOGITS
    ona
    0.98
    ley
    0.95
    nick
    0.91
    alia
    0.90
    inski
    0.90
    isha
    0.89
    itz
    0.89
    enh
    0.88
    en
    0.87
    ich
    0.86
    Act Density 0.510%

    No Known Activations