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

    Neuronpedia

    INDEX
    Explanations

    names followed by a country or position

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "aur."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Perspective
    -0.71
     Winchester
    -0.67
     Shroud
    -0.66
     Hue
    -0.66
     ECO
    -0.66
     Plays
    -0.66
     goto
    -0.64
     Cue
    -0.63
     Sparkle
    -0.62
     Proced
    -0.62
    POSITIVE LOGITS
    issan
    1.13
    aur
    1.10
    idon
    0.99
    thur
    0.94
    anamo
    0.89
    uses
    0.88
    asma
    0.88
    itan
    0.85
    itor
    0.85
    icular
    0.84
    Act Density 0.009%

    No Known Activations