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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elig
    -0.17
    ifiable
    -0.17
    å¦ĥ
    -0.16
    ched
    -0.15
    åŀ
    -0.15
    aat
    -0.15
    ufen
    -0.14
    /compiler
    -0.14
     denen
    -0.14
    geh
    -0.14
    POSITIVE LOGITS
    agna
    0.17
    bj
    0.15
    olen
    0.15
    ctr
    0.15
    erval
    0.14
     anyone
    0.14
     Nim
    0.14
    bjerg
    0.13
    icot
    0.13
    erton
    0.13
    Act Density 0.201%

    No Known Activations