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

    Neuronpedia

    INDEX
    Explanations

    special ASCII art patterns

    oai_token-act-pair · gpt-3.5-turbo

    various forms of punctuation and graphical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endors
    -0.73
     proble
    -0.71
     mesmer
    -0.71
     wearable
    -0.70
     nodd
    -0.69
     contribut
    -0.68
     retrospective
    -0.66
     bount
    -0.66
     consequential
    -0.66
     asset
    -0.66
    POSITIVE LOGITS
    -|
    1.49
    -.
    1.40
    -+
    1.34
    \-
    1.34
    -'
    1.30
    =-
    1.30
    =(
    1.28
    =/
    1.27
    âĸł
    1.27
    -,
    1.26
    Act Density 0.155%

    No Known Activations