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

    Neuronpedia

    INDEX
    Explanations

    references to scientific data and figures in a research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enci
    -0.15
    ede
    -0.15
    elu
    -0.15
    adero
    -0.15
    umpt
    -0.14
    ERA
    -0.14
    ald
    -0.13
    enco
    -0.13
    ำ
    -0.13
    umb
    -0.13
    POSITIVE LOGITS
    }
    0.21
    },
    0.21
    },↵↵
    0.18
    }.
    0.17
    uada
    0.16
    };
    0.16
    }:
    0.15
    },↵
    0.15
    abis
    0.14
     */,
    0.14
    Act Density 0.024%

    No Known Activations