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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    repetitive uses of the pronoun "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     funer
    -0.58
    idth
    -0.58
    911
    -0.56
     Polk
    -0.54
    quist
    -0.54
    hips
    -0.54
     appointments
    -0.53
     anten
    -0.52
     Columb
    -0.51
    Priv
    -0.50
    POSITIVE LOGITS
    zbollah
    0.86
    unes
    0.85
    alian
    0.84
    self
    0.83
    chy
    0.82
    iner
    0.74
    chwitz
    0.73
    ueller
    0.72
    zik
    0.69
    achi
    0.69
    Act Density 0.252%

    No Known Activations