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

    Neuronpedia

    INDEX
    Explanations

    vocabulary related to choices and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĽ²
    -0.16
    UNT
    -0.16
    Worksheet
    -0.15
    rame
    -0.15
    uzey
    -0.14
    æ°Ĺãģ«åħ¥
    -0.14
    unt
    -0.14
    527
    -0.14
    aversable
    -0.14
    vision
    -0.14
    POSITIVE LOGITS
    apesh
    0.15
    óng
    0.15
    expo
    0.14
    nem
    0.13
    iltr
    0.13
    estroy
    0.13
    å·±
    0.13
    å¿
    0.13
     Stud
    0.13
    tain
    0.13
    Act Density 0.091%

    No Known Activations