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

    Neuronpedia

    INDEX
    Explanations

    references to information inside brackets or encoded data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eighth
    -0.19
     eighth
    -0.18
    enville
    -0.16
    imed
    -0.16
    fal
    -0.15
    redient
    -0.15
    اÙĨÙĩ
    -0.15
    ibri
    -0.14
     gain
    -0.14
     }};↵
    -0.14
    POSITIVE LOGITS
    19
    0.63
    18
    0.57
     nineteen
    0.43
     nineteenth
    0.39
     eighteen
    0.38
    019
    0.37
    018
    0.33
    Û±Û¹
    0.32
     ninete
    0.32
    Û±Û¸
    0.32
    Act Density 0.069%

    No Known Activations