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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" indicating commitment or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĹĦ
    -0.16
    Łèĥ½
    -0.16
    gii
    -0.14
    apons
    -0.14
    ulers
    -0.14
    ean
    -0.14
    )prepare
    -0.14
    tility
    -0.14
    rens
    -0.14
    itals
    -0.13
    POSITIVE LOGITS
    .um
    0.16
    ament
    0.16
    isÃŃ
    0.15
     Yue
    0.14
    owell
    0.14
    acon
    0.14
     Surg
    0.14
    é
    0.14
     Psi
    0.13
     exactly
    0.13
    Act Density 0.023%

    No Known Activations