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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or questioning the status quo

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wr
    -0.15
    asics
    -0.15
    usalem
    -0.14
    uspend
    -0.14
    ertz
    -0.13
     beg
    -0.13
    zet
    -0.13
    uggage
    -0.13
    achinery
    -0.13
    ää
    -0.13
    POSITIVE LOGITS
    mens
    0.16
    .Horizontal
    0.15
    lest
    0.14
    maj
    0.14
     GetLastError
    0.14
    _YUV
    0.14
    åģ¶
    0.14
    exus
    0.14
    asa
    0.13
     CType
    0.13
    Act Density 0.576%

    No Known Activations