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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts, often indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     use
    -0.29
     Use
    -0.28
    use
    -0.25
    çĶ¨
    -0.24
    -use
    -0.24
    Use
    -0.23
    _use
    -0.23
    .use
    -0.23
     using
    -0.22
     uses
    -0.21
    POSITIVE LOGITS
     great
    0.26
     advantage
    0.25
     aid
    0.23
     supplement
    0.20
     good
    0.20
    great
    0.20
     complement
    0.19
     varying
    0.18
     guide
    0.18
     aide
    0.18
    Act Density 0.134%

    No Known Activations