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

    Neuronpedia

    INDEX
    Explanations

    programming-related variables and paths used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itat
    -0.14
    aya
    -0.14
    виÑĤ
    -0.14
     precinct
    -0.14
    os
    -0.14
    ķĮ
    -0.13
    angu
    -0.13
    buz
    -0.13
    uco
    -0.13
    /form
    -0.13
    POSITIVE LOGITS
    antha
    0.15
    ÅĻich
    0.14
    deaux
    0.14
    ystack
    0.14
    quette
    0.14
    gan
    0.14
    arhus
    0.14
    dating
    0.14
    lrt
    0.14
    esz
    0.13
    Act Density 0.125%

    No Known Activations