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

    Neuronpedia

    INDEX
    Explanations

    images or pictures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "photo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensable
    -0.89
    ricular
    -0.79
    merce
    -0.77
    ressive
    -0.75
    ulhu
    -0.73
    uese
    -0.73
    rane
    -0.72
    phasis
    -0.68
    urities
    -0.67
    avanaugh
    -0.67
    POSITIVE LOGITS
    journal
    1.14
    ynthesis
    1.05
    >>>>>>>>
    0.99
    photos
    0.98
     illustration
    0.90
     shoot
    0.88
     shoots
    0.87
    electric
    0.87
     album
    0.83
     Phot
    0.82
    Act Density 0.032%

    No Known Activations