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

    Neuronpedia

    INDEX
    Explanations

    adverbs related to frequency and probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uren
    -0.15
    cae
    -0.14
    inch
    -0.13
    ÂĿ
    -0.13
     سپس
    -0.13
    iae
    -0.13
    rf
    -0.13
    çĴ
    -0.13
    okin
    -0.13
    âĢļ
    -0.12
    POSITIVE LOGITS
     ones
    0.23
    ché
    0.19
    ebek
    0.18
     because
    0.17
    withstanding
    0.17
     those
    0.16
    nila
    0.16
    indow
    0.16
    mente
    0.15
     as
    0.15
    Act Density 0.136%

    No Known Activations