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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and question marks that indicate inquiries or prompts for information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pooled
    -0.81
     facult
    -0.72
     lact
    -0.68
     reciprocal
    -0.67
     marine
    -0.66
     deliber
    -0.65
     fish
    -0.65
     automatic
    -0.64
     polic
    -0.63
     threaded
    -0.63
    POSITIVE LOGITS
     Firstly
    0.99
     Its
    0.80
     Flavoring
    0.79
    SourceFile
    0.77
    Buzz
    0.77
    esides
    0.76
     Especially
    0.75
    Firstly
    0.75
     Particularly
    0.74
     Personally
    0.73
    Act Density 0.541%

    No Known Activations