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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to documenting visual content

    oai_token-act-pair · gpt-3.5-turbo

    references to documentation and capturing visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ycle
    -0.74
    ortium
    -0.68
    ardi
    -0.68
    tarians
    -0.68
    aneers
    -0.65
    osi
    -0.65
    esson
    -0.64
    sters
    -0.64
    ento
    -0.63
    tackle
    -0.63
    POSITIVE LOGITS
     likeness
    0.95
     images
    0.92
     silhouette
    0.91
     silhou
    0.90
     landscapes
    0.87
     holog
    0.87
     reality
    0.85
     skyline
    0.83
     phenomena
    0.83
     helpless
    0.82
    Act Density 0.404%

    No Known Activations