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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms indicating the concept of "addition."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANE
    -0.16
    виÑĩай
    -0.15
    اش
    -0.14
    /GPL
    -0.14
     ficken
    -0.14
    ogl
    -0.14
    geois
    -0.13
    .sponge
    -0.13
    rypton
    -0.13
    ane
    -0.13
    POSITIVE LOGITS
    arcer
    0.17
    leton
    0.15
    ÑĮ
    0.14
    ols
    0.14
    ordinary
    0.14
    ording
    0.14
    mers
    0.14
    ORD
    0.13
     Intern
    0.13
    orer
    0.13
    Act Density 0.019%

    No Known Activations