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

    Neuronpedia

    INDEX
    Explanations

    words related to pruning or trimming

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    EVA
    -0.72
    WARE
    -0.69
     Decay
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
     silenced
    -0.67
     AMERICA
    -0.66
    WIND
    -0.65
    ŃĶ
    -0.63
    heid
    -0.62
    requires
    -0.62
    POSITIVE LOGITS
    imming
    1.11
    acing
    1.05
    idget
    1.02
    ighter
    1.02
    aced
    1.01
    unn
    1.00
    icked
    1.00
    indle
    1.00
    anc
    0.99
    agged
    0.98
    Act Density 0.011%

    No Known Activations