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

    Neuronpedia

    INDEX
    Explanations

    adverbs

    oai_token-act-pair · gpt-3.5-turbo

    terms that emphasize authenticity or purity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !:
    -0.72
    !'"
    -0.69
     Millions
    -0.67
     moreover
    -0.66
     Chips
    -0.66
     thereby
    -0.65
     Liberation
    -0.64
     indeed
    -0.63
    !!!!!
    -0.63
    HAEL
    -0.62
    POSITIVE LOGITS
     niche
    0.84
     chronological
    0.82
     nic
    0.77
     stagnant
    0.75
    chal
    0.75
     descriptive
    0.75
     rough
    0.73
     anecdotal
    0.72
     passive
    0.71
    typ
    0.71
    Act Density 0.510%

    No Known Activations