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

    Neuronpedia

    INDEX
    Explanations

    numbers with units of measure

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WARN
    -0.66
     NP
    -0.59
     FS
    -0.58
     GF
    -0.55
     BG
    -0.52
     FG
    -0.52
     CM
    -0.51
     hindsight
    -0.51
    ãĤ°
    -0.48
     CB
    -0.48
    POSITIVE LOGITS
     respectively
    1.00
    )).
    0.90
    .).
    0.89
     attRot
    0.89
    .''.
    0.88
    .(
    0.87
    *.
    0.86
    +.
    0.86
    !.
    0.81
    %.
    0.80
    Act Density 1.479%

    No Known Activations