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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oader
    -0.15
    scri
    -0.15
    ipes
    -0.14
    _BITS
    -0.14
    enance
    -0.14
    bane
    -0.14
    alen
    -0.14
    alnız
    -0.14
    lrt
    -0.14
     chairman
    -0.14
    POSITIVE LOGITS
     per
    0.31
     follows
    0.30
     above
    0.25
     below
    0.24
     soon
    0.24
     seen
    0.24
     shown
    0.23
    yn
    0.23
     described
    0.23
    ych
    0.22
    Act Density 0.124%

    No Known Activations