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

    Neuronpedia

    INDEX
    Explanations

    usage of prepositions and words indicating change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    缮
    -0.15
    orida
    -0.15
    loff
    -0.15
    κοÏĤ
    -0.15
    ocs
    -0.15
    Å¡nÃŃ
    -0.14
    ÑĥÑĢÑģ
    -0.14
    linky
    -0.14
    å±Ĭ
    -0.14
    iaux
    -0.14
    POSITIVE LOGITS
    243
    0.16
     ones
    0.15
     бÑĥ
    0.15
     gen
    0.14
     bli
    0.14
    pin
    0.14
    ecome
    0.14
     instead
    0.14
     shower
    0.14
     sar
    0.13
    Act Density 0.185%

    No Known Activations