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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 't' and variations of accented characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imd
    -0.16
    ags
    -0.16
    abi
    -0.16
    727
    -0.15
    898
    -0.15
    cp
    -0.14
    ARSER
    -0.14
    heet
    -0.14
    RTL
    -0.14
    оÑĥ
    -0.14
    POSITIVE LOGITS
    vor
    0.18
    ward
    0.18
    vard
    0.17
    ematic
    0.17
    zv
    0.17
    gere
    0.16
    кан
    0.16
     Trot
    0.16
    аÑĢ
    0.15
    ilda
    0.15
    Act Density 0.008%

    No Known Activations