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

    Neuronpedia

    INDEX
    Explanations

    references to online content and academic resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĻµ
    -0.19
    cela
    -0.18
     ped
    -0.17
     arbit
    -0.15
    anje
    -0.15
    FFE
    -0.14
    okable
    -0.14
    ped
    -0.14
    ARSE
    -0.14
     Initialise
    -0.14
    POSITIVE LOGITS
    obe
    0.17
    erez
    0.15
    otti
    0.15
    ĥģ
    0.14
     Pemb
    0.14
    owski
    0.14
     PTR
    0.14
     Contributor
    0.13
    ha
    0.13
    364
    0.13
    Act Density 0.014%

    No Known Activations