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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.70
    IQ
    -0.66
    ONSORED
    -0.66
    below
    -0.65
     contained
    -0.64
    vich
    -0.64
     spawned
    -0.64
    contained
    -0.64
     transmitted
    -0.63
     pitted
    -0.63
    POSITIVE LOGITS
     grips
    1.06
     fruition
    0.84
     blows
    0.81
     conclusions
    0.81
     prominence
    0.79
     realise
    0.78
     congratulate
    0.76
    talk
    0.76
     realize
    0.74
     settle
    0.70
    Act Density 0.104%

    No Known Activations