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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ;
    -0.74
       
    -0.73
    </caption>
    -0.71
    Referencer
    -0.70
    NUMX
    -0.69
     שוליים
    -0.69
     quæ
    -0.69
    ]),
    -0.68
     ainfi
    -0.68
     simplifié
    -0.65
    POSITIVE LOGITS
     FUCKING
    0.72
     fucking
    0.68
     guys
    0.68
     wasnt
    0.67
     thing
    0.67
     etc
    0.67
    .....
    0.66
     ppl
    0.66
     sucks
    0.66
     guy
    0.65
    Act Density 0.402%

    No Known Activations