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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.69
     HasFactory
    -0.69
     Dyck
    -0.64
     whoſe
    -0.63
    UnusedPrivate
    -0.63
     Jefus
    -0.62
     pleaſure
    -0.62
    Пото
    -0.61
     SIAM
    -0.60
     poitrine
    -0.60
    POSITIVE LOGITS
     thing
    1.30
     something
    1.30
    thing
    1.26
    something
    1.23
     things
    1.23
     cosa
    1.20
    THING
    1.17
    Something
    1.16
     Thing
    1.16
    Thing
    1.15
    Act Density 0.147%

    No Known Activations