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

    Neuronpedia

    INDEX
    Explanations

    things related to depth or intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deep"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dule
    -0.83
    ULE
    -0.82
    ICAN
    -0.81
    icans
    -0.80
    Ĥİ
    -0.76
    ccess
    -0.70
    ICA
    -0.69
    PLE
    -0.67
    cules
    -0.66
    CENT
    -0.66
    POSITIVE LOGITS
     deep
    1.03
     depth
    0.90
     vein
    0.90
    ened
    0.87
     penetration
    0.87
    deep
    0.86
     depths
    0.83
     seeded
    0.83
     deepest
    0.82
     deeper
    0.81
    Act Density 0.011%

    No Known Activations