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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional statements or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sko
    -0.15
    ghi
    -0.14
    ermann
    -0.14
    ses
    -0.14
    kj
    -0.13
    er
    -0.13
    ollapse
    -0.13
     Margaret
    -0.13
     Hansen
    -0.13
    osph
    -0.13
    POSITIVE LOGITS
     upon
    0.35
    upon
    0.26
     Upon
    0.25
    Upon
    0.23
    æĸ¼
    0.21
    äºİ
    0.21
     whether
    0.20
     äºİ
    0.19
     on
    0.19
    ä¹İ
    0.17
    Act Density 0.011%

    No Known Activations