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

    Neuronpedia

    INDEX
    Explanations

    words related to deep locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Deep" followed by various terms, indicating a focus on the "Deep" genre or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cules
    -0.85
     Speedway
    -0.72
    ICAN
    -0.71
    icans
    -0.71
    Ń·
    -0.70
    uably
    -0.69
    代
    -0.69
     IMAGES
    -0.66
    ULE
    -0.65
    hett
    -0.64
    POSITIVE LOGITS
    water
    0.96
    ened
    0.91
     vein
    0.90
    redo
    0.81
    deep
    0.80
    est
    0.80
    ness
    0.79
    bent
    0.79
    ly
    0.76
    light
    0.74
    Act Density 0.006%

    No Known Activations