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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a sense of brightness or elevation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.17
    ka
    -0.15
    ous
    -0.15
    ÙĥÙĪ
    -0.14
    lip
    -0.14
    kate
    -0.14
    undler
    -0.14
     ifndef
    -0.14
    éļª
    -0.14
    tons
    -0.13
    POSITIVE LOGITS
    ToPoint
    0.19
    eh
    0.18
    erdale
    0.17
     ÑģÑĢедÑģÑĤв
    0.15
    enko
    0.14
    WEEN
    0.14
    icum
    0.14
    FormsModule
    0.14
    ););↵
    0.14
    ibern
    0.14
    Act Density 0.122%

    No Known Activations