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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limits, regulations, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.17
     jan
    -0.16
    1
    -0.16
     starting
    -0.15
     Jan
    -0.15
    iden
    -0.14
     once
    -0.14
    åijĢ
    -0.14
     eff
    -0.13
    once
    -0.13
    POSITIVE LOGITS
     present
    0.18
     Present
    0.17
     presente
    0.17
    ecut
    0.17
    noinspection
    0.16
    #End
    0.16
    present
    0.16
    deaux
    0.16
    ãģ¾ãģ§
    0.16
    LOPT
    0.16
    Act Density 0.068%

    No Known Activations