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

    Neuronpedia

    INDEX
    Explanations

    names starting with "Nik"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transplant
    -0.69
    pection
    -0.69
     starved
    -0.64
    ornia
    -0.63
    HAEL
    -0.61
     toll
    -0.61
     LSD
    -0.59
    ruary
    -0.58
     shocks
    -0.57
    dylib
    -0.57
    POSITIVE LOGITS
    nik
    0.74
    styles
    0.71
    construct
    0.69
    anski
    0.69
     Telescope
    0.68
    lez
    0.66
    tainment
    0.66
     Ascend
    0.66
    walker
    0.65
    vec
    0.65
    Act Density 0.419%

    No Known Activations