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

    Neuronpedia

    INDEX
    Explanations

    contrasting statements or ideas

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparison or contrasting statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ça
    -0.78
    stall
    -0.65
     Pasadena
    -0.65
     mul
    -0.60
     Allaah
    -0.60
     cosmos
    -0.60
     floor
    -0.60
     overfl
    -0.59
     Malaysia
    -0.59
     Beverly
    -0.58
    POSITIVE LOGITS
    awei
    0.81
    SPONSORED
    0.77
    DragonMagazine
    0.74
    chart
    0.72
    lihood
    0.70
    dogs
    0.67
    ombat
    0.66
     Flask
    0.66
     Gutenberg
    0.66
     Ratings
    0.66
    Act Density 0.017%

    No Known Activations