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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a return or a re-engagement with something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wahl
    -0.19
    bote
    -0.17
    OLT
    -0.15
    ibold
    -0.15
    iji
    -0.14
    imb
    -0.14
    _soft
    -0.14
    adro
    -0.14
    æľŁ
    -0.14
    GGLE
    -0.14
    POSITIVE LOGITS
     affairs
    0.15
     Heller
    0.15
    pg
    0.14
     Bean
    0.14
    oop
    0.14
    umin
    0.14
     Erg
    0.14
    .libs
    0.14
    pread
    0.13
     sha
    0.13
    Act Density 0.225%

    No Known Activations