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

    Neuronpedia

    INDEX
    Explanations

    words related to programmatic arguments and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ary
    -0.18
     rfl
    -0.15
    of
    -0.15
    arios
    -0.15
    Slave
    -0.15
    ìķĻ
    -0.15
    yi
    -0.15
    ÐĶÐļ
    -0.14
    vers
    -0.14
    orie
    -0.14
    POSITIVE LOGITS
    amerate
    0.16
    tec
    0.15
    æķħ
    0.15
    uru
    0.14
    adoo
    0.14
    intree
    0.14
    indle
    0.14
    itr
    0.14
    목
    0.14
    .hw
    0.14
    Act Density 0.006%

    No Known Activations