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

    Neuronpedia

    INDEX
    Explanations

    words that express comparisons and contrasts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esh
    -0.14
     literal
    -0.14
     weekly
    -0.13
     textual
    -0.13
    idal
    -0.13
    -0.13
     permutations
    -0.13
     modulo
    -0.13
    ypical
    -0.13
     gratis
    -0.13
    POSITIVE LOGITS
     problem
    0.16
    маз
    0.16
     job
    0.16
     thing
    0.15
     story
    0.15
    thing
    0.15
     solution
    0.15
     problema
    0.15
     Olympics
    0.15
    ÂĿ
    0.15
    Act Density 0.661%

    No Known Activations