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

    Neuronpedia

    INDEX
    Explanations

    terms related to success and failure in a testing or validation context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ZF
    -0.15
    ors
    -0.15
    ÑĮ
    -0.15
     pent
    -0.14
    -prepend
    -0.14
     cogn
    -0.14
     Rem
    -0.14
    pent
    -0.14
    ake
    -0.14
     Weber
    -0.14
    POSITIVE LOGITS
    Scrollbar
    0.16
    nze
    0.16
    ÙħÙĨد
    0.14
    ackbar
    0.14
    ì§Ī
    0.14
     Stam
    0.14
    물
    0.14
    ))^
    0.14
    heimer
    0.13
    hire
    0.13
    Act Density 0.013%

    No Known Activations