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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that introduce alternative scenarios or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ldr
    -0.18
    }elseif
    -0.16
    gs
    -0.15
    atters
    -0.14
     either
    -0.14
    elden
    -0.14
     EITHER
    -0.13
    ildo
    -0.13
     anz
    -0.13
    ottenham
    -0.13
    POSITIVE LOGITS
     merely
    0.18
     jist
    0.17
     just
    0.16
    something
    0.15
     же
    0.15
    egen
    0.15
    deaux
    0.14
    éģĵè·¯
    0.14
    acom
    0.14
    Just
    0.14
    Act Density 0.037%

    No Known Activations