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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "see" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onet
    -0.18
    ri
    -0.17
    ̣
    -0.16
    se
    -0.15
     nonatomic
    -0.15
    ish
    -0.15
    ãģĦãĤĭ
    -0.15
    ecd
    -0.15
    protocols
    -0.15
     sire
    -0.14
    POSITIVE LOGITS
     whether
    0.29
     how
    0.28
    æĺ¯åIJ¦
    0.20
     Whether
    0.19
     why
    0.19
    whether
    0.18
     what
    0.18
    how
    0.18
    210
    0.17
    å°¿
    0.16
    Act Density 0.023%

    No Known Activations