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

    Neuronpedia

    INDEX
    Explanations

    action verbs indicating progression or change in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     INLINE
    -0.14
    stderr
    -0.14
    INLINE
    -0.13
    /up
    -0.13
    _void
    -0.13
    Offline
    -0.13
    /off
    -0.13
    ави
    -0.13
     Wolff
    -0.13
    plings
    -0.13
    POSITIVE LOGITS
     out
    1.05
    -out
    0.88
    out
    0.79
    åĩº
    0.62
    -Out
    0.60
    _out
    0.58
    Out
    0.57
     Out
    0.56
    	out
    0.56
    åĩºçļĦ
    0.55
    Act Density 0.115%

    No Known Activations