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

    Neuronpedia

    INDEX
    Explanations

    numerical representations and entities' names related to taxonomy or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulers
    -0.15
    534
    -0.15
    коÑĤ
    -0.15
    inputs
    -0.14
    _hook
    -0.14
    tat
    -0.14
    541
    -0.14
    rlen
    -0.14
     Å¡tÄĽ
    -0.14
     inputs
    -0.13
    POSITIVE LOGITS
     shells
    0.33
     shell
    0.29
    shell
    0.27
    Shell
    0.26
     Shell
    0.24
    -shell
    0.23
     moll
    0.22
     vá»ı
    0.19
     sn
    0.19
     Patel
    0.18
    Act Density 0.007%

    No Known Activations