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

    Neuronpedia

    INDEX
    Explanations

    the presence of questions and references to reasoning or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhan
    -0.16
    mite
    -0.15
    orate
    -0.15
    atr
    -0.15
    abr
    -0.14
    lope
    -0.14
    ohana
    -0.14
    orris
    -0.14
     Herman
    -0.14
    eren
    -0.13
    POSITIVE LOGITS
     Holder
    0.19
    uvw
    0.14
     Ae
    0.14
    éŁ
    0.14
     issue
    0.14
    _nested
    0.14
    	throws
    0.13
    183
    0.13
     exception
    0.13
     Pearson
    0.13
    Act Density 0.026%

    No Known Activations