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

    Neuronpedia

    INDEX
    Explanations

    numbers in a sequence with symbolic notation

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that may indicate formatting issues or non-standard text representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Libyan
    -0.66
     Droid
    -0.63
     scattering
    -0.63
     charm
    -0.60
     board
    -0.60
     scatter
    -0.60
     retreat
    -0.58
     miscarriage
    -0.58
     Moroccan
    -0.57
     radius
    -0.57
    POSITIVE LOGITS
    ¹
    1.11
    ¢
    0.93
    Į
    0.91
    ı
    0.90
    º
    0.89
    Ĵ
    0.88
    £
    0.87
    agree
    0.85
    Ĭ
    0.84
    say
    0.83
    Act Density 0.269%

    No Known Activations