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

    Neuronpedia

    INDEX
    Explanations

    prepositions preceding examples or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zona
    -0.62
    chenko
    -0.62
    LAB
    -0.60
    Norm
    -0.59
    Ag
    -0.58
    olan
    -0.58
     Devils
    -0.57
    Enlarge
    -0.57
    marine
    -0.56
    Champ
    -0.55
    POSITIVE LOGITS
     example
    1.38
     instance
    1.36
    bidden
    1.32
    gotten
    1.05
    geries
    1.01
     reasons
    1.00
    bid
    1.00
    cing
    0.97
    gery
    0.97
     starters
    0.95
    Act Density 0.056%

    No Known Activations