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

    Neuronpedia

    INDEX
    Explanations

    the preposition 'to'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to" and its variations, indicating infinitive verbs or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shown
    -0.74
    ropolitan
    -0.66
    cyclopedia
    -0.62
    Interstitial
    -0.62
     PRESS
    -0.60
    quartered
    -0.59
    capt
    -0.59
    particularly
    -0.59
    lap
    -0.58
    ailability
    -0.57
    POSITIVE LOGITS
    aucus
    0.87
    oiler
    0.69
    hew
    0.68
     congr
    0.66
     goodbye
    0.64
     sacrific
    0.63
     âĶľâĶĢâĶĢ
    0.62
    iatus
    0.62
    endor
    0.61
     temptation
    0.61
    Act Density 0.122%

    No Known Activations