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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to," particularly in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    žil
    -0.15
     antlr
    -0.15
     ç¿
    -0.15
    elts
    -0.14
    quam
    -0.14
    instein
    -0.14
    ork
    -0.14
    ivol
    -0.14
    abbage
    -0.14
    éĽij
    -0.13
    POSITIVE LOGITS
     suit
    0.35
     reflect
    0.33
     fit
    0.32
     suits
    0.28
     match
    0.28
    fit
    0.28
     Suit
    0.27
    reflect
    0.27
     suite
    0.26
     Reflect
    0.25
    Act Density 0.091%

    No Known Activations