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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibilities or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amik
    -0.15
    ilen
    -0.15
     rub
    -0.14
     Hass
    -0.14
    ibia
    -0.14
    asy
    -0.14
    ami
    -0.14
    ardon
    -0.13
     alone
    -0.13
    499
    -0.13
    POSITIVE LOGITS
    ovy
    0.15
    ewire
    0.15
    lore
    0.15
    icle
    0.14
    ë¦Ħ
    0.14
    arge
    0.14
    .UnitTesting
    0.14
    ÑĢим
    0.13
    parity
    0.13
    شتر
    0.13
    Act Density 0.027%

    No Known Activations