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

    Neuronpedia

    INDEX
    Explanations

    specific patterns or sequences in text, particularly focusing on structural elements and shifts in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ialog
    -0.15
    evin
    -0.14
     Its
    -0.13
    )((((
    -0.13
    egov
    -0.13
    iв
    -0.13
    STREAM
    -0.12
    _HT
    -0.12
     friendship
    -0.12
    Its
    -0.12
    POSITIVE LOGITS
     Dress
    0.16
     millennia
    0.15
     dress
    0.15
    React
    0.15
     react
    0.15
     reacted
    0.15
    ibur
    0.15
     centuries
    0.14
     Surprise
    0.14
     caracter
    0.14
    Act Density 0.020%

    No Known Activations