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

    Neuronpedia

    INDEX
    Explanations

    locations or specific places within sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.86
    tarian
    -0.72
    istries
    -0.69
     glim
    -0.66
     caucuses
    -0.65
     suspic
    -0.65
     newsp
    -0.65
     incorrectly
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.64
     superpower
    -0.64
    POSITIVE LOGITS
     Regist
    0.79
     Levant
    0.74
     Amen
    0.73
    please
    0.72
    ño
    0.72
     lang
    0.71
     Ney
    0.71
     alle
    0.70
    eds
    0.68
    lé
    0.68
    Act Density 0.199%

    No Known Activations