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

    Neuronpedia

    INDEX
    Explanations

    pronouns and related words, including words related to personal actions and reflections

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts or actions related to "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holding
    -0.71
     Frontier
    -0.66
     Pirates
    -0.64
     Passenger
    -0.64
     Dyn
    -0.63
     Nano
    -0.63
     Aluminum
    -0.62
     PLAN
    -0.60
     Planetary
    -0.60
     GPS
    -0.59
    POSITIVE LOGITS
    alian
    1.00
     oneself
    0.98
    self
    0.86
     undermines
    0.85
     beforehand
    0.84
     anew
    0.84
     afterwards
    0.82
    iner
    0.81
    chy
    0.79
     involves
    0.79
    Act Density 0.172%

    No Known Activations