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

    Neuronpedia

    INDEX
    Explanations

    formatted elements or analytical components in discussions about data or links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eighth
    -0.19
     Eighth
    -0.18
    enville
    -0.15
    errick
    -0.15
    arters
    -0.15
    imed
    -0.14
    ải
    -0.14
    ibri
    -0.14
    redient
    -0.14
     Wick
    -0.14
    POSITIVE LOGITS
    18
    0.68
    19
    0.68
     nineteen
    0.45
     eighteen
    0.45
     nineteenth
    0.43
    019
    0.39
    018
    0.39
    åįģåħ«
    0.36
     ninete
    0.35
    Û±Û¸
    0.35
    Act Density 0.065%

    No Known Activations