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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating requests for user reviews and testimonials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Torch
    -0.16
    ÄĻd
    -0.15
    026
    -0.14
     accompagn
    -0.14
     Peaks
    -0.14
     Brow
    -0.14
    AAA
    -0.14
    ival
    -0.14
    iller
    -0.14
    /MIT
    -0.14
    POSITIVE LOGITS
    udu
    0.17
    Subsystem
    0.16
    ultipart
    0.15
    oldem
    0.15
    quez
    0.14
    ÑıÑĩ
    0.14
     pisc
    0.14
    zos
    0.14
    ertos
    0.14
    cplusplus
    0.14
    Act Density 0.027%

    No Known Activations