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

    Neuronpedia

    INDEX
    Explanations

    prepositions or phrases indicating direction or influence

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "to" and related phrases indicating intention or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.72
    È
    -0.71
    querque
    -0.71
     congr
    -0.65
    amiya
    -0.65
    furt
    -0.64
    meric
    -0.63
    oop
    -0.63
     launches
    -0.62
    chan
    -0.61
    POSITIVE LOGITS
     tighter
    0.70
    kefeller
    0.68
     gradually
    0.65
    pload
    0.64
     modem
    0.64
     fruition
    0.63
     theirs
    0.62
     Mutant
    0.62
     unim
    0.61
     outweigh
    0.60
    Act Density 0.463%

    No Known Activations