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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    endings of sentences or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bound
    -0.65
    GN
    -0.64
    leg
    -0.61
    Bomb
    -0.60
    aqu
    -0.60
    ASC
    -0.59
    MX
    -0.57
    MP
    -0.57
    cash
    -0.56
    INC
    -0.56
    POSITIVE LOGITS
    姫
    0.90
    abwe
    0.83
    Ó
    0.77
    ãĥ¼ãĥĨ
    0.77
    uyomi
    0.77
    ãĤ¼ãĤ¦ãĤ¹
    0.76
    ¬¼
    0.74
    ulty
    0.73
    theless
    0.72
    ãĥĨãĤ£
    0.71
    Act Density 0.149%

    No Known Activations