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

    Neuronpedia

    INDEX
    Explanations

    first person singular pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    sentences that emphasize the speaker's personal experiences or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Constitutional
    -0.79
     Triple
    -0.72
     Newspaper
    -0.66
     PRESS
    -0.66
     Rugby
    -0.64
     Cameroon
    -0.62
     Uganda
    -0.61
     Patterson
    -0.59
     Transgender
    -0.59
     newspaper
    -0.58
    POSITIVE LOGITS
    uler
    1.05
    pher
    0.91
    urat
    0.81
    'll
    0.77
     shouldn
    0.75
    llular
    0.75
     dunno
    0.75
    iji
    0.74
    athered
    0.74
     could
    0.71
    Act Density 0.137%

    No Known Activations