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

    Neuronpedia

    INDEX
    Explanations

    references to setting and achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esa
    -0.19
    ei
    -0.16
    eme
    -0.16
    eso
    -0.15
    kh
    -0.15
    elden
    -0.15
    ese
    -0.15
    lak
    -0.14
    vore
    -0.14
    uve
    -0.14
    POSITIVE LOGITS
    /target
    0.18
    inalg
    0.16
    ightly
    0.15
    óst
    0.15
    led
    0.14
    charset
    0.14
    hlen
    0.14
    lessly
    0.14
    swith
    0.14
    tır
    0.14
    Act Density 0.029%

    No Known Activations