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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ty
    -0.17
    Ty
    -0.16
    esan
    -0.16
    WORD
    -0.15
    wahl
    -0.15
    esen
    -0.14
    浩
    -0.14
    ialized
    -0.14
    ив
    -0.14
    ä¼į
    -0.14
    POSITIVE LOGITS
     Sigma
    0.15
    eta
    0.15
     Î
    0.15
    碼
    0.14
    ishing
    0.14
    ropri
    0.14
    ÑĸÑĤи
    0.14
    haar
    0.14
    etro
    0.13
    INGTON
    0.13
    Act Density 0.012%

    No Known Activations