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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "of" and other related prepositions or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Numerous
    -0.19
    大éĩı
    -0.19
     lots
    -0.18
     Lots
    -0.18
    lots
    -0.17
     and
    -0.17
     portions
    -0.16
     Many
    -0.16
     Portions
    -0.16
    Certain
    -0.16
    POSITIVE LOGITS
     different
    0.21
     them
    0.19
     mostly
    0.18
     interconnected
    0.18
     differently
    0.18
     fairly
    0.17
     sorts
    0.16
    different
    0.16
     possible
    0.15
    them
    0.15
    Act Density 0.240%

    No Known Activations