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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gpt-3.5-turbo

    hexadecimal values or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geon
    -0.73
     clipboard
    -0.72
    warts
    -0.71
     simplicity
    -0.70
    geons
    -0.70
    agall
    -0.70
    indal
    -0.66
    stood
    -0.65
    ween
    -0.65
     aversion
    -0.64
    POSITIVE LOGITS
    fff
    1.04
    0100
    1.02
    ffff
    0.98
    0000
    0.96
    0002
    0.91
    001
    0.90
    015
    0.88
    00000
    0.87
    },{"
    0.85
    0000000
    0.85
    Act Density 0.036%

    No Known Activations