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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ija
    -0.15
    zeros
    -0.14
    иÑģÑĮ
    -0.14
    03
    -0.14
    alue
    -0.13
    three
    -0.13
    -mf
    -0.13
    two
    -0.13
     zeros
    -0.13
    30
    -0.13
    POSITIVE LOGITS
    1
    0.56
     unity
    0.41
    ï¼ij
    0.40
    Û±
    0.37
     one
    0.37
     ONE
    0.36
    .ONE
    0.35
    -one
    0.34
    -One
    0.34
     One
    0.33
    Act Density 0.175%

    No Known Activations