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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their usages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âl
    -0.15
     adher
    -0.15
     Donovan
    -0.15
     Barth
    -0.15
    rup
    -0.15
    unga
    -0.15
     shall
    -0.15
    uli
    -0.14
    andr
    -0.14
    t
    -0.14
    POSITIVE LOGITS
     be
    0.19
    atrix
    0.17
    kova
    0.16
     check
    0.15
     contact
    0.15
    (æĹ¥
    0.15
     undermin
    0.15
    .timedelta
    0.14
    GetMethod
    0.14
     Remember
    0.14
    Act Density 0.005%

    No Known Activations