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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to," indicating instructions or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tas
    -0.17
    ÃŁen
    -0.15
    uce
    -0.15
    .Modules
    -0.15
    .ak
    -0.15
    æݪ
    -0.14
    pone
    -0.14
    åĽ
    -0.14
    rios
    -0.14
    ox
    -0.14
    POSITIVE LOGITS
    iang
    0.17
    Cette
    0.15
    elerik
    0.15
    ych
    0.15
    pector
    0.14
    ieder
    0.14
    gings
    0.14
    chk
    0.14
    ewood
    0.13
    ëħĦìĹIJ
    0.13
    Act Density 0.040%

    No Known Activations