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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the conclusion or ending of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oss
    -0.17
    le
    -0.15
    ich
    -0.15
    otal
    -0.15
    <<<<<<<
    -0.15
    sel
    -0.14
    iche
    -0.14
    leme
    -0.14
    och
    -0.14
    à¹īาà¸Ĭ
    -0.14
    POSITIVE LOGITS
    icina
    0.18
    -the
    0.17
    abbo
    0.17
    ushima
    0.16
     thumb
    0.16
    анов
    0.16
    course
    0.16
    afone
    0.16
     affairs
    0.16
     course
    0.16
    Act Density 0.052%

    No Known Activations