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

    Neuronpedia

    INDEX
    Explanations

    names and biographical data of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.15
    pson
    -0.15
     itself
    -0.14
    ัวร
    -0.14
    asl
    -0.14
    awl
    -0.13
     خص
    -0.13
    ropoda
    -0.13
    bere
    -0.13
    onto
    -0.13
    POSITIVE LOGITS
     (;
    0.22
     adalah
    0.21
     better
    0.20
     lÃł
    0.19
     sometimes
    0.19
     wis
    0.18
    æĺ¯ä¸Ģ
    0.18
     Listen
    0.17
     est
    0.17
     commonly
    0.16
    Act Density 0.052%

    No Known Activations