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

    Neuronpedia

    INDEX
    Explanations

    photo captions from a series of photos

    oai_token-act-pair · gpt-3.5-turbo

    references to photos or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ministic
    -0.81
    merce
    -0.76
    phas
    -0.76
    mie
    -0.68
    stood
    -0.68
     gentleman
    -0.67
    rane
    -0.66
    oshenko
    -0.66
     speech
    -0.65
    ocrin
    -0.64
    POSITIVE LOGITS
     Photos
    1.00
    Gallery
    0.89
     Caption
    0.86
    ynthesis
    0.82
    Photos
    0.79
    OTOS
    0.72
     Annotations
    0.72
     Photo
    0.70
     )]
    0.70
     Timeline
    0.68
    Act Density 0.009%

    No Known Activations