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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ("../../
    -0.49
     and
    -0.49
    aktor
    -0.48
     The
    -0.44
    gnon
    -0.43
    eser
    -0.42
    Datuak
    -0.41
    zustellen
    -0.41
    The
    -0.41
    ("../
    -0.41
    POSITIVE LOGITS
     myſelf
    1.01
    发表于
    0.87
     chofe
    0.84
    FTFY
    0.82
     Theſe
    0.81
     disambiguazione
    0.78
    etheless
    0.78
    MigrationBuilder
    0.78
    __":
    0.77
     defire
    0.77
    Act Density 0.178%

    No Known Activations