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

    Neuronpedia

    INDEX
    Explanations

    references to photographs or images

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.72
    imore
    -0.71
    ollah
    -0.69
    riched
    -0.66
    otomy
    -0.64
    rane
    -0.63
    ModLoader
    -0.62
     unch
    -0.61
    uckle
    -0.60
    rete
    -0.60
    POSITIVE LOGITS
     Credit
    0.83
    journal
    0.82
     Gallery
    0.81
     gallery
    0.80
     snapped
    0.77
     courtesy
    0.74
     caption
    0.73
    Shop
    0.72
     illustration
    0.71
    credit
    0.71
    Act Density 0.016%

    No Known Activations