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

    Neuronpedia

    INDEX
    Explanations

    references to important concepts or noteworthy observations in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĿãģĵ
    -0.16
    utas
    -0.14
    adera
    -0.14
     ÑĤакими
    -0.13
    ạch
    -0.13
    raquo
    -0.13
    uft
    -0.12
    enas
    -0.12
    omy
    -0.12
    obec
    -0.12
    POSITIVE LOGITS
     worth
    0.28
     missing
    0.23
     about
    0.22
     that
    0.19
     Worth
    0.18
     stood
    0.18
     lacking
    0.18
     unique
    0.17
    worth
    0.17
    _about
    0.17
    Act Density 0.111%

    No Known Activations