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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that suggest improvement or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licity
    -0.16
    enco
    -0.16
    tol
    -0.16
    vid
    -0.16
    izzo
    -0.15
    iven
    -0.15
    adÃŃ
    -0.14
    QC
    -0.14
    _tol
    -0.14
    lish
    -0.13
    POSITIVE LOGITS
     than
    0.40
     THAN
    0.30
     Than
    0.30
    than
    0.29
    Than
    0.28
     nor
    0.27
    _than
    0.25
     než
    0.23
     except
    0.22
    -than
    0.22
    Act Density 0.036%

    No Known Activations