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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names related to various fields such as individuals, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    phrasings that indicate the existence or status of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     targ
    -0.71
    )|
    -0.63
     goodbye
    -0.63
     *)
    -0.62
    ,[
    -0.61
     derby
    -0.59
     qualification
    -0.58
    ,)
    -0.58
    âĢķ
    -0.58
     Meridian
    -0.57
    POSITIVE LOGITS
    etheless
    1.29
    senal
    0.80
     nonetheless
    0.77
     nevertheless
    0.75
    ŃĶ
    0.73
     hereby
    0.73
    rils
    0.67
    hement
    0.67
    ategory
    0.67
    Ļ½
    0.67
    Act Density 0.456%

    No Known Activations