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

    Neuronpedia

    INDEX
    Explanations

    words related to mechanical levers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gdala
    -0.86
    soever
    -0.75
    care
    -0.74
    Ĥª
    -0.71
    hw
    -0.70
    ĻĤ
    -0.70
    eh
    -0.70
    Ĥ¬
    -0.70
    CAST
    -0.68
    ħĭ
    -0.67
    POSITIVE LOGITS
    aged
    1.17
    agement
    0.98
    ages
    0.97
    aging
    0.90
    agements
    0.88
    age
    0.85
    ange
    0.77
    itures
    0.74
    ational
    0.72
    ulic
    0.72
    Act Density 0.113%

    No Known Activations