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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns as subjects followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that indicate collective actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peak
    -0.74
    noon
    -0.67
     Outside
    -0.65
    iatus
    -0.64
    earch
    -0.64
    tains
    -0.64
    Outside
    -0.63
     Previous
    -0.63
    Around
    -0.62
     Relief
    -0.62
    POSITIVE LOGITS
    'll
    0.90
    orio
    0.83
    swick
    0.77
     reasoned
    0.77
    prus
    0.76
    reditary
    0.76
    'd
    0.75
     nevertheless
    0.75
    ãĤ¤ãĥĪ
    0.75
    've
    0.73
    Act Density 0.744%

    No Known Activations