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

    Neuronpedia

    INDEX
    Explanations

    terms related to health conditions and their social implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     such
    -0.18
    such
    -0.17
    éĤ£ç§į
    -0.16
    ardown
    -0.15
    397
    -0.15
    umont
    -0.15
     SUCH
    -0.15
    è¿Ļä¸Ģ
    -0.15
    ặng
    -0.15
    rowable
    -0.14
    POSITIVE LOGITS
     themselves
    0.21
    curity
    0.17
    ìłĢ
    0.17
     guys
    0.15
    eker
    0.15
    arest
    0.14
    ateful
    0.14
    bell
    0.14
    -ci
    0.14
     along
    0.13
    Act Density 0.136%

    No Known Activations