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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abbo
    -0.15
    ithe
    -0.15
    ä¸ĺ
    -0.14
    à¸Ńà¸Ķ
    -0.14
    層
    -0.14
    usher
    -0.14
    laz
    -0.14
    OTE
    -0.14
    trand
    -0.14
    pite
    -0.14
    POSITIVE LOGITS
     else
    0.25
     Nobody
    0.19
    except
    0.19
     ever
    0.19
     except
    0.18
    /no
    0.17
    else
    0.16
    aten
    0.15
    ël
    0.15
     ELSE
    0.15
    Act Density 0.025%

    No Known Activations