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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "happen" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }{*}{
    -0.52
     Bibliothe
    -0.50
    SourceChecksum
    -0.49
    wiſe
    -0.48
    phinx
    -0.48
     Denise
    -0.48
     Ensign
    -0.48
    ConstraintMaker
    -0.47
    minWidth
    -0.46
    Denise
    -0.46
    POSITIVE LOGITS
    happen
    1.21
     happen
    1.11
     happening
    1.09
    happened
    1.08
     happens
    1.07
    happens
    1.06
     Happened
    1.05
     Happen
    1.04
     Happening
    1.04
     happenings
    1.03
    Act Density 0.206%

    No Known Activations