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

    Neuronpedia

    INDEX
    Explanations

    references to published works, including their titles and editors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text following punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    publisher locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unknownFields
    -0.43
    PropertyChanging
    -0.43
     Mix
    -0.43
     pies
    -0.42
     @"/
    -0.41
    מך
    -0.40
     cake
    -0.38
     mix
    -0.38
    cake
    -0.38
     '{@
    -0.38
    POSITIVE LOGITS
     Efq
    0.77
     purpoſe
    0.75
     ſeveral
    0.69
     betweenstory
    0.68
     myſelf
    0.68
     propOrder
    0.66
     pleaſure
    0.64
     themſelves
    0.64
     actionMode
    0.63
     dieß
    0.63
    Act Density 0.242%

    No Known Activations