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

    Neuronpedia

    INDEX
    Explanations

    references to categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prot
    -0.16
    Ì
    -0.15
    ìĸ´ëĤĺ
    -0.15
     PROT
    -0.15
    à¥Īद
    -0.15
     ба
    -0.14
    ̣
    -0.14
     Forces
    -0.14
    tom
    -0.14
     Graham
    -0.14
    POSITIVE LOGITS
    mour
    0.18
    etin
    0.16
    νι
    0.15
    etta
    0.15
    otics
    0.14
    incident
    0.14
    Pale
    0.14
    ानन
    0.14
    hw
    0.13
    缮
    0.13
    Act Density 0.000%

    No Known Activations