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

    Neuronpedia

    INDEX
    Explanations

    references to unknown or unspecified quantities and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iros
    -0.17
    utow
    -0.15
    fur
    -0.15
    ichick
    -0.14
    icana
    -0.14
    /videos
    -0.14
    .LA
    -0.14
    Ìī
    -0.14
    bilt
    -0.14
    åijĬ
    -0.14
    POSITIVE LOGITS
    123
    0.16
    umber
    0.15
    415
    0.15
     olan
    0.15
    uco
    0.15
    ip
    0.14
    olini
    0.14
    514
    0.14
    ÙĬات
    0.14
    mh
    0.13
    Act Density 0.158%

    No Known Activations