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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.70
    idad
    -0.66
    uyomi
    -0.66
    Enlarge
    -0.64
     starve
    -0.62
    ithering
    -0.61
    ãĤ¼
    -0.61
    oiler
    -0.61
    agy
    -0.60
    REF
    -0.60
    POSITIVE LOGITS
     course
    1.05
     FIG
    0.94
     sorts
    0.93
     each
    0.90
     ours
    0.78
    course
    0.77
     yours
    0.76
     theirs
    0.71
    containing
    0.68
     Adren
    0.67
    Act Density 0.248%

    No Known Activations