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

    Neuronpedia

    INDEX
    Explanations

    patterns resembling ASCII art of different characters

    oai_token-act-pair · gpt-3.5-turbo

    patterns of special characters and symbols used in text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presenter
    -0.72
     presentations
    -0.70
     immersion
    -0.68
     sleeper
    -0.67
     eyewitness
    -0.67
     Steele
    -0.67
     viability
    -0.66
     presentation
    -0.64
     toddler
    -0.64
     consensus
    -0.63
    POSITIVE LOGITS
    +=
    1.48
    \-
    1.46
    -+
    1.46
    =/
    1.46
    ^
    1.45
    -|
    1.44
    =-
    1.42
    \)
    1.42
    -+-+
    1.42
    ^{
    1.40
    Act Density 0.077%

    No Known Activations