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

    Neuronpedia

    INDEX
    Explanations

    words related to constraints or limitations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to concerns or issues, particularly in socio-economic or environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dos
    -0.84
    cules
    -0.82
    sonian
    -0.79
    ctors
    -0.78
    pei
    -0.76
    pmwiki
    -0.72
    sbm
    -0.72
    htt
    -0.72
    jong
    -0.71
    grab
    -0.71
    POSITIVE LOGITS
    ellation
    1.39
    abulary
    1.25
    ipation
    1.24
    itution
    1.09
    expr
    1.06
    rict
    1.06
    ricted
    1.04
    ricting
    1.00
    rued
    0.98
    ruction
    0.97
    Act Density 0.016%

    No Known Activations