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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize individual items or components within a larger context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     all
    -0.17
    avail
    -0.16
    ury
    -0.16
    ute
    -0.14
    angen
    -0.14
    ίκ
    -0.14
    aily
    -0.14
    wide
    -0.14
    trak
    -0.14
    oga
    -0.14
    POSITIVE LOGITS
     respective
    0.24
     separately
    0.23
    çĭ¬ç«ĭ
    0.22
     respectively
    0.21
     unique
    0.19
     differently
    0.18
    .AutoComplete
    0.18
    çį¨
    0.17
     distinct
    0.17
     separate
    0.17
    Act Density 0.167%

    No Known Activations