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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a noun phrase, indicating actions taking place

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ists
    -0.72
    Bey
    -0.72
    Ul
    -0.70
    YY
    -0.70
    resy
    -0.70
    ista
    -0.66
    ennes
    -0.63
    ILA
    -0.63
    ;;;;
    -0.61
    ν
    -0.61
    POSITIVE LOGITS
     behalf
    1.77
     improving
    1.00
     developing
    0.88
     projects
    0.86
     refining
    0.79
    eday
    0.79
     solving
    0.79
     Capitol
    0.78
     securing
    0.77
     optimizing
    0.77
    Act Density 0.083%

    No Known Activations