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

    Neuronpedia

    INDEX
    Explanations

    elements related to computational processes and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walton
    -0.15
    à¹ģส
    -0.14
     Mog
    -0.14
     pod
    -0.14
     Grip
    -0.14
    Volume
    -0.13
    ↵↵
    -0.13
    *scale
    -0.13
    drag
    -0.13
     Bren
    -0.13
    POSITIVE LOGITS
     corpor
    0.29
     glove
    0.28
     Corpor
    0.25
     коÑĢпÑĥÑģ
    0.24
     Token
    0.23
     Sent
    0.23
     corpus
    0.23
     tokenizer
    0.23
     word
    0.23
     sentiment
    0.22
    Act Density 0.043%

    No Known Activations