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

    Neuronpedia

    INDEX
    Explanations

    certain vowel and consonant patterns in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thôi
    -0.16
    ughters
    -0.15
     UNU
    -0.15
    kili
    -0.14
    iped
    -0.14
    ippy
    -0.14
    trinsic
    -0.14
    umba
    -0.14
     Wich
    -0.13
    _Float
    -0.13
    POSITIVE LOGITS
     gre
    0.18
    .sections
    0.15
     alf
    0.14
    âĢª
    0.14
     Dob
    0.14
    enever
    0.13
    DbType
    0.13
    burg
    0.13
    atego
    0.13
    ç´°
    0.13
    Act Density 0.272%

    No Known Activations