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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating admission or confession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ales
    -0.15
    reative
    -0.15
     Pied
    -0.14
     Fet
    -0.13
    Ùĩ
    -0.13
    vais
    -0.13
    ade
    -0.13
    eft
    -0.13
    trak
    -0.13
    CHR
    -0.13
    POSITIVE LOGITS
    duc
    0.17
    že
    0.16
    orative
    0.16
     admitted
    0.16
    ders
    0.15
    ducible
    0.15
    221
    0.15
    phere
    0.15
     admission
    0.15
     admit
    0.15
    Act Density 0.047%

    No Known Activations