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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific research and scientific evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ics
    -0.17
    atics
    -0.16
    ual
    -0.16
    uma
    -0.15
    ibilities
    -0.15
    ær
    -0.15
    letes
    -0.15
    еком
    -0.14
    aban
    -0.14
    umatic
    -0.14
    POSITIVE LOGITS
    ally
    0.36
    ALLY
    0.28
    xfff
    0.16
    s
    0.16
     BaseService
    0.16
    âĶĶ
    0.15
    ska
    0.14
    _cast
    0.14
    -grade
    0.14
    oster
    0.14
    Act Density 0.015%

    No Known Activations