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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating a comparison or increase in quantity or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esch
    -0.17
    egade
    -0.15
     sab
    -0.15
    ianne
    -0.15
    alım
    -0.14
    è´
    -0.14
    allery
    -0.14
    ãĥ¥ãĥ¼
    -0.13
    /rfc
    -0.13
     Khan
    -0.13
    POSITIVE LOGITS
     than
    0.25
     THAN
    0.23
    than
    0.21
    -than
    0.21
     Than
    0.21
    Than
    0.19
     než
    0.19
    _than
    0.19
     niż
    0.17
    iry
    0.15
    Act Density 0.195%

    No Known Activations