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

    Neuronpedia

    INDEX
    Explanations

    numbers and numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shapeshifter
    -0.75
    yre
    -0.71
    gans
    -0.68
    wow
    -0.64
    hip
    -0.63
    ci
    -0.63
    vous
    -0.63
    posed
    -0.63
    edged
    -0.62
    imov
    -0.61
    POSITIVE LOGITS
    Ô
    0.82
     Bleach
    0.65
    --------------------------------------------------------
    0.63
    اÙĦ
    0.62
     à¨
    0.60
    ¯¯¯¯¯¯¯¯
    0.57
     EntityItem
    0.56
    utenberg
    0.55
    galitarian
    0.55
     Remastered
    0.53
    Act Density 0.067%

    No Known Activations