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

    Neuronpedia

    INDEX
    Explanations

    specific instructions or requests

    oai_token-act-pair · gpt-3.5-turbo

    references to attachments or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "?
    -0.66
     };
    -0.65
    "}],"
    -0.65
     });
    -0.64
    "],"
    -0.63
    ().
    -0.63
    });
    -0.62
    "},
    -0.61
    };
    -0.60
     boo
    -0.60
    POSITIVE LOGITS
    bledon
    0.74
    ngth
    0.65
    ammy
    0.62
    olars
    0.61
    ibur
    0.60
    silver
    0.60
    akespeare
    0.57
    yip
    0.57
    encers
    0.57
    anchester
    0.57
    Act Density 0.966%

    No Known Activations