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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gathering or verifying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anke
    -0.16
    ä¹ĭä¸Ģ
    -0.14
    ople
    -0.14
    adele
    -0.13
    onya
    -0.13
    plet
    -0.13
    /from
    -0.13
    oso
    -0.13
    ëĭ
    -0.13
    .idea
    -0.13
    POSITIVE LOGITS
     which
    0.48
     whether
    0.38
     Which
    0.37
     if
    0.36
     WHICH
    0.35
    which
    0.34
    Which
    0.33
     what
    0.31
     wich
    0.28
     exactly
    0.28
    Act Density 0.211%

    No Known Activations