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

    Neuronpedia

    INDEX
    Explanations

    instances of rarity and exceptional qualities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berger
    -0.18
    ayo
    -0.17
    loth
    -0.15
    omu
    -0.15
    ieten
    -0.15
    Äĩi
    -0.14
    ienne
    -0.14
    758
    -0.14
    LIKELY
    -0.14
    864
    -0.14
    POSITIVE LOGITS
     occasional
    0.30
     exceptions
    0.30
     occasionally
    0.28
     Exceptions
    0.27
     few
    0.26
     Occasionally
    0.26
     handful
    0.25
     quelques
    0.25
     exception
    0.24
    few
    0.24
    Act Density 0.295%

    No Known Activations