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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values and their associations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     especially
    -0.19
    especially
    -0.17
    particularly
    -0.17
     besonders
    -0.16
     particularly
    -0.16
    Åĵ
    -0.15
    å°¤
    -0.15
     indeed
    -0.14
     оÑģобенно
    -0.14
     пÑĢÑıмо
    -0.14
    POSITIVE LOGITS
     another
    0.36
     counting
    0.36
    another
    0.30
    åı¦
    0.26
    plus
    0.26
     two
    0.26
     Another
    0.25
     plus
    0.25
    Another
    0.25
    two
    0.23
    Act Density 0.124%

    No Known Activations