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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uition
    -0.17
    ency
    -0.16
    nown
    -0.14
    depend
    -0.14
    ional
    -0.14
    actic
    -0.14
    uit
    -0.14
    icken
    -0.14
    ol
    -0.14
    g
    -0.14
    POSITIVE LOGITS
     quote
    0.26
     paraph
    0.23
    onces
    0.21
     me
    0.19
     Quote
    0.17
    quote
    0.17
    å¤Ħ
    0.17
     date
    0.16
    ledo
    0.16
     wit
    0.16
    Act Density 0.044%

    No Known Activations