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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whiff
    -0.69
     weaving
    -0.69
     thwart
    -0.68
     mathemat
    -0.68
     weave
    -0.66
     recycling
    -0.66
     invis
    -0.64
     chunks
    -0.64
     synerg
    -0.64
     pigeon
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.77
    âĢ
    1.34
     âĢº
    1.26
     âĢ
    1.10
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.07
    âĸł
    1.05
    ðŁ
    1.03
    ï¸
    1.02
     (@
    1.02
    âĸ¬âĸ¬
    1.01
    Act Density 0.181%

    No Known Activations