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

    Neuronpedia

    INDEX
    Explanations

    examples of contrasting situations or ideas

    oai_token-act-pair · gpt-3.5-turbo

    the word "also" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nce
    -0.78
    orse
    -0.78
    tten
    -0.76
     meanwhile
    -0.66
    essor
    -0.65
    isher
    -0.65
    ishers
    -0.64
    Exit
    -0.64
    ater
    -0.64
    article
    -0.64
    POSITIVE LOGITS
     contains
    0.78
     includes
    0.77
    cially
    0.76
     serves
    0.75
     incorporates
    0.73
     insofar
    0.73
     cautioned
    0.73
     occasionally
    0.72
     encourages
    0.72
     reflects
    0.71
    Act Density 0.087%

    No Known Activations