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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "op."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iciary
    -1.85
     facts
    -1.63
    journal
    -1.62
    ungen
    -1.60
    isten
    -1.51
    naire
    -1.51
    arios
    -1.49
    smen
    -1.48
    ĥ½
    -1.46
    enstein
    -1.45
    POSITIVE LOGITS
     forward
    1.61
    .’”
    1.59
    .’
    1.58
    oming
    1.54
    cling
    1.53
    aping
    1.52
     slow
    1.51
     downward
    1.50
    ative
    1.48
     rainbow
    1.46
    Act Density 0.171%

    No Known Activations