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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values or quantities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongo
    -0.16
    ocop
    -0.16
    yne
    -0.15
    apiro
    -0.14
     Harm
    -0.14
    apt
    -0.14
    ing
    -0.14
    osu
    -0.14
    ych
    -0.14
    spe
    -0.14
    POSITIVE LOGITS
    orden
    0.17
    qua
    0.15
     TOD
    0.15
    -sama
    0.15
    theless
    0.15
    .ci
    0.14
     latter
    0.14
    âĸ¡âĸ¡
    0.14
    urs
    0.13
    ullah
    0.13
    Act Density 0.036%

    No Known Activations