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

    Neuronpedia

    INDEX
    Explanations

    references to Creative Commons licensing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Predictor
    -0.16
    },{"
    -0.16
    inch
    -0.15
    ington
    -0.15
    iens
    -0.15
    ago
    -0.14
     men
    -0.14
    HCI
    -0.14
     deb
    -0.14
    okus
    -0.14
    POSITIVE LOGITS
    inya
    0.16
    UNT
    0.15
    æļ
    0.15
     excer
    0.15
     Bent
    0.14
    uire
    0.14
     -*-č↵
    0.14
    .opend
    0.14
    ssp
    0.14
    usercontent
    0.13
    Act Density 0.006%

    No Known Activations