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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the abbreviation 'ng'

    oai_token-act-pair · gpt-3.5-turbo

    the suffix 'ng' in various contexts, indicating an interest in continuous actions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.73
    apter
    -0.65
    IELD
    -0.63
    ãĥ
    -0.62
    balls
    -0.61
    ãĥ¤
    -0.60
     Ezek
    -0.60
     2600
    -0.60
    UNCH
    -0.59
     Brach
    -0.59
    POSITIVE LOGITS
    roup
    1.14
    roups
    1.12
    oing
    1.07
    thening
    1.05
    allery
    1.01
    emouth
    0.97
    lish
    0.96
    regor
    0.95
    lasses
    0.95
    thens
    0.94
    Act Density 0.018%

    No Known Activations