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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs or potential actions

    oai_token-act-pair · gpt-3.5-turbo

    the first-person pronoun "I" and its various usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Failure
    -0.67
    PF
    -0.65
     Eternity
    -0.62
    ¿½
    -0.62
    services
    -0.62
     Mormonism
    -0.61
     Witt
    -0.61
    Tan
    -0.61
    dylib
    -0.60
     Harm
    -0.59
    POSITIVE LOGITS
    'll
    1.08
     figured
    1.03
     decided
    1.01
     opted
    0.97
    ctic
    0.96
     shouldn
    0.96
     resorted
    0.92
     guess
    0.90
     gotta
    0.90
     gladly
    0.89
    Act Density 0.119%

    No Known Activations