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

    Neuronpedia

    INDEX
    Explanations

    verbs ending in 'ing' and 'ed' that show continuity or completion of actions

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skydragon
    -0.65
    abit
    -0.64
    wagen
    -0.63
    anche
    -0.60
    isc
    -0.59
    antam
    -0.59
    ailability
    -0.58
    earchers
    -0.57
    izons
    -0.57
    opens
    -0.57
    POSITIVE LOGITS
    urally
    0.75
    LY
    0.75
    adoes
    0.73
    ly
    0.72
    soever
    0.69
    aneously
    0.68
    ulate
    0.63
    lihood
    0.62
    SHIP
    0.61
    yy
    0.61
    Act Density 0.287%

    No Known Activations