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

    Neuronpedia

    INDEX
    Explanations

    gerunds ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.87
    luaj
    -0.79
     actionGroup
    -0.65
    å£
    -0.63
    itars
    -0.62
    SIGN
    -0.59
    ufact
    -0.58
    OHN
    -0.58
     unim
    -0.57
    ivari
    -0.57
    POSITIVE LOGITS
    redients
    1.16
    tons
    1.06
    atio
    0.83
    athering
    0.82
    ding
    0.81
    hots
    0.76
    ering
    0.75
    roup
    0.74
    stad
    0.74
    ication
    0.74
    Act Density 0.070%

    No Known Activations