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

    Neuronpedia

    INDEX
    Explanations

    mentions of cuts or cutting objects

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "cut" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grace
    -0.74
     Directorate
    -0.71
    SPONSORED
    -0.69
     Kamp
    -0.69
     Moder
    -0.69
    BUS
    -0.66
    AMP
    -0.65
    issance
    -0.63
     Refresh
    -0.61
     Administrator
    -0.58
    POSITIVE LOGITS
    scene
    1.45
    scenes
    1.37
    lasses
    1.32
    thro
    1.31
    aneous
    1.27
    lass
    1.19
    tle
    1.12
    away
    1.12
    ters
    1.08
    aways
    1.06
    Act Density 0.036%

    No Known Activations