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

    Neuronpedia

    INDEX
    Explanations

    instances where someone's actions or statements are being judged or interpreted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when" and related conjunctions and clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yourselves
    -0.66
    Our
    -0.55
    Your
    -0.54
    MY
    -0.52
    tty
    -0.51
    Consider
    -0.50
    }}}
    -0.50
    ugu
    -0.49
     Our
    -0.49
    ourt
    -0.49
    POSITIVE LOGITS
     he
    1.78
     she
    1.65
    she
    1.38
    he
    1.27
    He
    1.16
     SHE
    1.14
     He
    1.05
    She
    1.04
     they
    1.04
    soever
    0.97
    Act Density 0.496%

    No Known Activations