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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    references to different individuals and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĺħ
    -0.62
    stars
    -0.59
    stem
    -0.59
    ju
    -0.59
    /
    -0.58
     THEM
    -0.58
    notice
    -0.58
    Monster
    -0.57
     Hazard
    -0.57
     Monster
    -0.57
    POSITIVE LOGITS
    éĹĺ
    0.80
    etter
    0.75
    arnaev
    0.71
    arily
    0.70
     rend
    0.67
    arov
    0.67
     adjourn
    0.65
    poral
    0.64
    essor
    0.63
     initials
    0.63
    Act Density 0.437%

    No Known Activations