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

    Neuronpedia

    INDEX
    Explanations

    the suffix "-ng" combined with a preceding word part

    oai_token-act-pair · gpt-3.5-turbo

    words related to agricultural companies and their practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.83
    ãĥ¯ãĥ³
    -0.72
    ãĥ¤
    -0.69
    ãĥī
    -0.66
    ãĥĹ
    -0.66
    acco
    -0.64
    BALL
    -0.62
    ãĥı
    -0.60
     lav
    -0.60
    Äĩ
    -0.60
    POSITIVE LOGITS
    roup
    1.16
    roups
    1.15
    thening
    1.09
    oing
    1.03
    thens
    1.03
    lish
    0.98
    lasses
    0.98
    inx
    0.96
    ong
    0.94
    raphics
    0.91
    Act Density 0.008%

    No Known Activations