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

    Neuronpedia

    INDEX
    Explanations

    words related to physical structures or actions involving construction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to establishing or creating structures and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izzle
    -0.81
    Dat
    -0.77
    uddin
    -0.76
     Sample
    -0.75
    essen
    -0.70
    rition
    -0.68
     Genie
    -0.67
     budget
    -0.66
     JD
    -0.66
    omics
    -0.66
    POSITIVE LOGITS
     erect
    3.33
     erected
    2.42
     erection
    2.35
     upright
    1.91
     resting
    1.42
     perched
    1.30
    rect
    1.26
     rested
    1.21
    pole
    1.18
     taller
    1.14
    Act Density 0.030%

    No Known Activations