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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating preference or evaluations of options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fron
    -0.14
    ÑĬ
    -0.14
     vur
    -0.14
    nemonic
    -0.14
    oba
    -0.13
    407
    -0.13
    uen
    -0.13
     fore
    -0.13
     nitrogen
    -0.13
    307
    -0.13
    POSITIVE LOGITS
    ongs
    0.18
    _transport
    0.17
     ÙĨÚ¯
    0.15
    ooke
    0.15
    ervo
    0.15
    iversit
    0.14
    &e
    0.14
    .flex
    0.14
    ê²Ģ
    0.13
    CLU
    0.13
    Act Density 0.056%

    No Known Activations