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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs representing actions or modifications of something

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" and variations of the pronoun "them."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Polk
    -0.67
     Sund
    -0.63
    idth
    -0.62
     Frontier
    -0.61
     abortions
    -0.60
     Radar
    -0.59
    heny
    -0.59
     Korea
    -0.59
    ãĥ©ãĥ³
    -0.59
     United
    -0.56
    POSITIVE LOGITS
    atic
    1.01
    self
    1.01
     accordingly
    1.01
    alian
    0.97
    selves
    0.94
    atically
    0.94
    iner
    0.81
    zbollah
    0.80
    atical
    0.79
     yourself
    0.77
    Act Density 0.130%

    No Known Activations