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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and codes

    oai_token-act-pair · gpt-3.5-turbo

    sequences of binary or hexadecimal values and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.71
    hurst
    -0.70
    erker
    -0.70
    wright
    -0.69
    arity
    -0.67
     necks
    -0.67
     joints
    -0.67
    FUL
    -0.64
    ouri
    -0.63
     bott
    -0.63
    POSITIVE LOGITS
    ãĥ¢
    0.93
    ãĥĥãĤ¯
    0.81
    fff
    0.79
    ãĥĹ
    0.74
    ãĥª
    0.74
    001
    0.74
    merce
    0.74
    0100
    0.72
    ffff
    0.71
    mercial
    0.70
    Act Density 0.031%

    No Known Activations