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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss the degree or range of something being evaluated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     django
    -0.77
    </b>
    -0.76
    Loire
    -0.71
    fertigung
    -0.70
     Chattanooga
    -0.68
    ganu
    -0.66
     nakalista
    -0.66
    </i>
    -0.66
    dymyr
    -0.66
     فريبيس
    -0.65
    POSITIVE LOGITS
    Extent
    1.34
     Extent
    1.31
    extent
    1.21
     extent
    1.15
     amount
    0.81
    près
    0.76
    BeginInit
    0.76
    Amount
    0.76
     />);
    0.75
     extender
    0.75
    Act Density 0.006%

    No Known Activations