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
    ipay
    -0.16
    aving
    -0.16
    utow
    -0.15
    urus
    -0.15
    depend
    -0.14
    ustral
    -0.14
    umen
    -0.13
     haf
    -0.13
    ro
    -0.13
    rial
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.16
    ieder
    0.16
    OTH
    0.15
     quote
    0.15
    137
    0.14
    .BorderFactory
    0.14
     paraph
    0.13
    UBLE
    0.13
    ì´Į
    0.13
    oth
    0.13
    Act Density 0.065%

    No Known Activations