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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating source or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leground
    -0.15
    Äħż
    -0.14
     Kirst
    -0.13
     Key
    -0.13
    UTOR
    -0.13
     Dere
    -0.13
    eller
    -0.13
    ssi
    -0.13
    Down
    -0.13
    rint
    -0.13
    POSITIVE LOGITS
    isci
    0.16
    _plain
    0.16
    nut
    0.15
    essen
    0.15
    imax
    0.14
    è¡¡
    0.14
    heimer
    0.14
     Nut
    0.14
    oftware
    0.14
    ****/↵
    0.14
    Act Density 0.024%

    No Known Activations