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

    Neuronpedia

    INDEX
    Explanations

    references to scientific researchers and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OCI
    -0.17
     Butt
    -0.15
    ãģķãĤī
    -0.14
    orst
    -0.14
    alc
    -0.14
    æ¯
    -0.14
    butt
    -0.13
    éĽĦ
    -0.13
    andas
    -0.13
    /tiny
    -0.13
    POSITIVE LOGITS
     themselves
    0.16
    ships
    0.14
    ocker
    0.14
    inging
    0.14
    ustil
    0.14
     thems
    0.14
    anch
    0.14
     UNIVERS
    0.14
    veau
    0.14
    enberg
    0.14
    Act Density 0.023%

    No Known Activations