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

    Neuronpedia

    INDEX
    Explanations

    modal verbs that express possibility, obligation, or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ever
    -0.17
    aid
    -0.17
    pz
    -0.16
    Ever
    -0.15
     ever
    -0.14
    affer
    -0.14
    odore
    -0.14
     Ever
    -0.14
    ç³»
    -0.14
    rias
    -0.14
    POSITIVE LOGITS
    cki
    0.15
    .djang
    0.15
    olum
    0.14
     lak
    0.14
    .Appearance
    0.14
    HIR
    0.13
     bom
    0.13
    èĦ±
    0.13
    .uml
    0.13
    coli
    0.13
    Act Density 0.388%

    No Known Activations