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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reading time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pou
    -0.15
    ili
    -0.14
     Polic
    -0.14
    ally
    -0.14
    sbin
    -0.13
    216
    -0.13
    imat
    -0.13
     Sist
    -0.13
     Colon
    -0.13
    vr
    -0.13
    POSITIVE LOGITS
     read
    0.22
    读
    0.20
     reading
    0.20
    è®Ģ
    0.19
     reads
    0.18
    -read
    0.18
    Reading
    0.17
    reads
    0.17
    reo
    0.16
     Reading
    0.16
    Act Density 0.018%

    No Known Activations