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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing trust or belief in the speaker's words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oce
    -0.17
    reads
    -0.15
    £
    -0.15
    utz
    -0.14
    kat
    -0.14
    'Ñı
    -0.14
    byname
    -0.13
     Nat
    -0.13
     subtotal
    -0.13
     whats
    -0.13
    POSITIVE LOGITS
    ONGL
    0.16
    >NN
    0.15
    ulet
    0.15
    enaire
    0.15
    oose
    0.15
    lia
    0.14
    ior
    0.14
    ergus
    0.14
    engkap
    0.14
    Ïĩι
    0.14
    Act Density 0.041%

    No Known Activations