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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" and its variations to identify singular subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atic
    -0.15
     Crosby
    -0.15
    aban
    -0.15
    adier
    -0.14
    hurst
    -0.14
    ewriter
    -0.14
    /authentication
    -0.14
     Hart
    -0.14
    asma
    -0.14
     rozp
    -0.13
    POSITIVE LOGITS
    esser
    0.15
    Spacing
    0.15
     Shields
    0.15
    ION
    0.15
    ivan
    0.14
    nam
    0.14
     Gar
    0.14
    ãĢģäºĮ
    0.14
     Hi
    0.13
     masses
    0.13
    Act Density 0.049%

    No Known Activations