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

    Neuronpedia

    INDEX
    Explanations

    content related to explanations and the act of clarifying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.17
    ager
    -0.15
    _ips
    -0.14
    achi
    -0.14
    gr
    -0.14
    ÅĻÃŃd
    -0.14
     Armour
    -0.14
    gan
    -0.14
    (PR
    -0.14
    achs
    -0.13
    POSITIVE LOGITS
     why
    0.24
    为ä»Ģä¹Ī
    0.20
     how
    0.17
    why
    0.17
    -away
    0.15
    awy
    0.15
    FFE
    0.15
    issa
    0.15
    tn
    0.15
     Away
    0.15
    Act Density 0.036%

    No Known Activations