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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate arrival or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theid
    -0.15
    teri
    -0.15
    gif
    -0.15
    leanup
    -0.14
    itas
    -0.14
    ĥ
    -0.14
    826
    -0.14
    oodle
    -0.14
    ibli
    -0.14
    hana
    -0.14
    POSITIVE LOGITS
    .hm
    0.15
    okt
    0.15
    adlo
    0.14
    -sample
    0.13
     Barney
    0.13
     <*>
    0.13
     tuition
    0.13
    179
    0.13
    otch
    0.13
     partie
    0.13
    Act Density 0.006%

    No Known Activations