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

    Neuronpedia

    INDEX
    Explanations

    references to changes in societal norms or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cplusplus
    -0.14
    Ïħνα
    -0.14
    ezi
    -0.13
     Dir
    -0.13
    omed
    -0.13
     ultimately
    -0.13
    Scoped
    -0.13
    åľ§
    -0.13
     buen
    -0.13
    ucas
    -0.13
    POSITIVE LOGITS
    pong
    0.16
    cent
    0.15
    bounds
    0.15
    ãģ£ãģ±
    0.15
    EFAULT
    0.15
     CENT
    0.15
     Ù¾ÚĺÙĪÙĩ
    0.14
    able
    0.14
     cent
    0.14
    780
    0.14
    Act Density 0.105%

    No Known Activations