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

    Neuronpedia

    INDEX
    Explanations

    acronyms related to professions or political subjects

    oai_token-act-pair · gpt-3.5-turbo

    forms of the prefix "pro-" followed by various suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     similarities
    -0.72
     ponds
    -0.70
    jriwal
    -0.68
     wells
    -0.66
     Skydragon
    -0.65
    ¥µ
    -0.64
    HF
    -0.63
     nurs
    -0.61
     nests
    -0.61
    fine
    -0.60
    POSITIVE LOGITS
    essional
    0.85
    cess
    0.85
    incial
    0.85
    etary
    0.81
    hetic
    0.78
    atural
    0.77
    imity
    0.75
     CTR
    0.75
    upt
    0.75
    cia
    0.74
    Act Density 0.060%

    No Known Activations