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

    Neuronpedia

    INDEX
    Explanations

    words related to martial arts and its history

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯ãĥ³
    -0.75
    IDER
    -0.69
    OME
    -0.68
    Ò
    -0.67
    urity
    -0.67
    ãĥ
    -0.67
    ERO
    -0.67
    ����
    -0.65
    Effective
    -0.64
    ãĥŀ
    -0.63
    POSITIVE LOGITS
    lasses
    1.31
    nir
    1.03
    regate
    1.01
    oing
    0.98
    sung
    0.91
    aroo
    0.90
    sten
    0.86
    culosis
    0.84
    undo
    0.84
    ratulations
    0.82
    Act Density 0.023%

    No Known Activations