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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain statistical data or numerical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peace
    -0.73
     bounty
    -0.72
     wellness
    -0.72
     compassionate
    -0.71
     hunger
    -0.71
     slick
    -0.69
     greenhouse
    -0.69
     altru
    -0.68
     safe
    -0.68
     garbage
    -0.67
    POSITIVE LOGITS
     Both
    1.48
     Finally
    1.44
     Either
    1.39
     Again
    1.36
     Lastly
    1.35
     Together
    1.34
     Neither
    1.30
     Regardless
    1.29
     Thus
    1.26
     Interestingly
    1.26
    Act Density 0.423%

    No Known Activations