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

    Neuronpedia

    INDEX
    Explanations

    discussions about procedural changes and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensi
    -0.16
    å¾ĴæŃ©
    -0.15
    agi
    -0.15
     att
    -0.15
    286
    -0.14
    GR
    -0.14
    sex
    -0.13
    unc
    -0.13
    .nd
    -0.13
    adar
    -0.13
    POSITIVE LOGITS
    ucch
    0.17
    ugen
    0.16
     внимание
    0.14
    аÑĤкÑĥ
    0.14
     Portions
    0.14
    IVAL
    0.14
    ohl
    0.14
    pNet
    0.14
     ÙĬتÙħ
    0.14
    antha
    0.14
    Act Density 0.320%

    No Known Activations