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

    Neuronpedia

    INDEX
    Explanations

    legal terms and concepts related to innocence and guilt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıж
    -0.15
     Angiospermae
    -0.12
    лÑıв
    -0.12
    zig
    -0.12
    ë³´ì¦Ŀê¸Ī
    -0.12
    ÙĪÙĤÙģ
    -0.12
    dez
    -0.12
    uguay
    -0.12
    .ov
    -0.12
    asal
    -0.12
    POSITIVE LOGITS
     added
    0.92
     addition
    0.91
     adding
    0.89
    æ·»åĬł
    0.84
     adds
    0.84
     add
    0.84
     additions
    0.82
     Adding
    0.82
     добав
    0.79
     Addition
    0.79
    Act Density 0.476%

    No Known Activations