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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and related infinitives or prepositions indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amen
    -0.16
     offsetY
    -0.15
    amber
    -0.15
    imuth
    -0.15
    ertia
    -0.15
    icos
    -0.14
    bé
    -0.14
    kazy
    -0.14
    lore
    -0.14
    ickey
    -0.14
    POSITIVE LOGITS
     vars
    0.20
    erva
    0.18
    licht
    0.17
     raised
    0.17
    udder
    0.17
    reau
    0.16
     Raised
    0.16
    erc
    0.15
     maneuver
    0.15
     Carrier
    0.15
    Act Density 0.020%

    No Known Activations