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

    Neuronpedia

    INDEX
    Explanations

    numbers mixed with various initials

    oai_token-act-pair · gpt-3.5-turbo

    quantitative expressions or references that indicate a decrease or lesser value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EDITION
    -0.70
     mine
    -0.69
     seam
    -0.60
     Fortune
    -0.59
     sim
    -0.57
     cutter
    -0.55
     MU
    -0.55
     mould
    -0.54
    ionage
    -0.54
     Ceres
    -0.54
    POSITIVE LOGITS
    Population
    0.77
    rawdownloadcloneembedreportprint
    0.73
    lehem
    0.71
    âĶĢâĶĢâĶĢâĶĢ
    0.69
    erion
    0.68
    skirts
    0.67
    aukee
    0.67
    Ire
    0.66
    Synopsis
    0.65
    ajor
    0.64
    Act Density 0.484%

    No Known Activations