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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailer
    -0.18
    raya
    -0.15
    istra
    -0.15
    irie
    -0.14
    opard
    -0.14
    pson
    -0.14
    _endian
    -0.14
    ifen
    -0.13
     plaisir
    -0.13
     Insecta
    -0.13
    POSITIVE LOGITS
    onna
    0.21
    ones
    0.20
     be
    0.20
    hem
    0.20
    nard
    0.19
     saja
    0.19
    ily
    0.17
    /all
    0.17
    est
    0.16
    ÏĮÏģ
    0.16
    Act Density 0.099%

    No Known Activations