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

    Neuronpedia

    INDEX
    Explanations

    terms related to decreasing or minimizing amounts or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uell
    -0.16
    amt
    -0.15
    ÅŁÄ±
    -0.15
    rieg
    -0.14
    ervoir
    -0.14
    hood
    -0.14
    æľĿ
    -0.14
    fulness
    -0.13
    itude
    -0.13
     fewer
    -0.13
    POSITIVE LOGITS
    oubles
    0.17
    vala
    0.15
    zens
    0.15
    оÑı
    0.15
    ely
    0.15
    adden
    0.14
    erin
    0.14
    EXTERN
    0.13
    aket
    0.13
    Expose
    0.13
    Act Density 0.042%

    No Known Activations