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

    Neuronpedia

    INDEX
    Explanations

    emotions and subjective experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of observation or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sanctuary
    -0.70
     kit
    -0.67
     AA
    -0.65
     AAA
    -0.65
     BMC
    -0.64
     HS
    -0.63
     shield
    -0.63
     board
    -0.62
     barrier
    -0.62
     ALS
    -0.62
    POSITIVE LOGITS
    ifully
    1.43
    rarily
    1.30
    identally
    1.21
    orically
    1.21
    prisingly
    1.19
    hematically
    1.18
    xtap
    1.18
    itionally
    1.16
    rary
    1.15
    ately
    1.15
    Act Density 0.223%

    No Known Activations