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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tıģ
    -0.15
    olla
    -0.14
    ester
    -0.14
    adel
    -0.14
     Pence
    -0.14
    nze
    -0.13
    ayer
    -0.13
     lent
    -0.13
    antry
    -0.13
    Ģ
    -0.13
    POSITIVE LOGITS
    /or
    0.19
    rog
    0.16
    üre
    0.15
    asa
    0.15
    lick
    0.14
    à¥Ĥड
    0.14
    agal
    0.14
     pots
    0.13
     Pot
    0.13
     Gle
    0.13
    Act Density 0.023%

    No Known Activations