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

    Neuronpedia

    INDEX
    Explanations

    references to professional roles and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lut
    -0.17
    lund
    -0.17
    992
    -0.15
    ùa
    -0.14
     Intermediate
    -0.14
    stell
    -0.14
    uos
    -0.14
    .tele
    -0.14
    asl
    -0.13
    fak
    -0.13
    POSITIVE LOGITS
    åı¦ä¸Ģ
    0.46
     another
    0.46
    another
    0.37
     otra
    0.37
     otro
    0.37
    åı¦
    0.36
    ãĤĤãģĨ
    0.36
     Another
    0.35
     opposite
    0.32
     дÑĢÑĥгой
    0.32
    Act Density 0.085%

    No Known Activations