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

    Neuronpedia

    INDEX
    Explanations

    terms related to projects or organizations with "org" in the name

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evict
    -0.65
    Fine
    -0.63
     restraining
    -0.63
     DOE
    -0.62
     notch
    -0.61
     probability
    -0.60
     retaliate
    -0.60
     consequence
    -0.58
     dunno
    -0.58
     prevailing
    -0.57
    POSITIVE LOGITS
    enson
    1.11
    ensen
    1.06
    ersen
    1.04
    roup
    1.04
    enstein
    1.02
    rade
    0.99
    enh
    0.97
    oso
    0.96
    sky
    0.96
    asms
    0.96
    Act Density 0.006%

    No Known Activations