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

    Neuronpedia

    INDEX
    Explanations

    words related to positions or locations

    oai_token-act-pair · gpt-3.5-turbo

    count nouns that indicate various categories or groups of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocracy
    -0.68
    cca
    -0.62
    aeda
    -0.60
    igun
    -0.58
     Ashes
    -0.57
    ghazi
    -0.56
     Relief
    -0.56
     Narr
    -0.55
     Corpus
    -0.55
    imaru
    -0.55
    POSITIVE LOGITS
    mith
    0.85
     sprang
    0.78
     logged
    0.75
     remain
    0.73
     dealt
    0.72
     remained
    0.70
     yielded
    0.70
     were
    0.69
     rescind
    0.68
     have
    0.68
    Act Density 0.303%

    No Known Activations