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

    Neuronpedia

    INDEX
    Explanations

    mentions of different variations or forms of English

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    translated
    -0.17
    usi
    -0.16
    Translated
    -0.15
    aq
    -0.15
    меÑī
    -0.15
     translated
    -0.14
    shal
    -0.14
    òng
    -0.14
     translator
    -0.14
    SSF
    -0.14
    POSITIVE LOGITS
     dialect
    0.19
     spoken
    0.18
     regional
    0.18
     speakers
    0.17
     Standard
    0.16
    073
    0.15
     Regional
    0.15
    spoken
    0.15
     orth
    0.15
     æ³
    0.15
    Act Density 0.045%

    No Known Activations