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

    Neuronpedia

    INDEX
    Explanations

    words related to giving presentations or talks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "presentation" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sey
    -0.70
    breeding
    -0.68
    leans
    -0.64
    lust
    -0.63
    kowski
    -0.63
    apped
    -0.62
    bered
    -0.62
    si
    -0.62
     solitary
    -0.62
    ritten
    -0.61
    POSITIVE LOGITS
     presentations
    1.02
     presentation
    0.94
     slides
    0.92
    eering
    0.83
    entary
    0.81
    nce
    0.79
    emonium
    0.78
    tion
    0.77
    tions
    0.76
     Present
    0.75
    Act Density 0.027%

    No Known Activations