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

    Neuronpedia

    INDEX
    Explanations

    verbs denoting action or transition

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or groups and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¢âĢ¢
    -0.66
    ÃĽ
    -0.65
    "}],"
    -0.65
     Differences
    -0.64
    ¬¼
    -0.58
    ieth
    -0.56
    soType
    -0.55
     Mehran
    -0.54
    imilation
    -0.53
    iencies
    -0.53
    POSITIVE LOGITS
     kinda
    1.18
     basically
    1.14
     supposedly
    1.13
     apparently
    1.13
     thankfully
    1.06
     reportedly
    1.05
     obviously
    1.04
     freaking
    1.03
     definitely
    1.03
     literally
    1.03
    Act Density 0.857%

    No Known Activations