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

    Neuronpedia

    INDEX
    Explanations

    repetitions of the word "none"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    typeorm
    -0.53
    goo
    -0.51
    aspectj
    -0.50
    semb
    -0.50
    iostream
    -0.50
    <table>
    -0.48
    nov
    -0.48
    ಟ್
    -0.47
     جه
    -0.47
     métier
    -0.47
    POSITIVE LOGITS
     obvious
    1.11
    obvious
    1.03
    obviously
    1.02
     obviously
    1.01
     Obviously
    0.95
    Obviously
    0.95
     none
    0.93
    Obvious
    0.93
     IMHO
    0.91
    UnsafeEnabled
    0.89
    Act Density 0.151%

    No Known Activations