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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a need for urgency or importance

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.78
     beard
    -0.77
     nodd
    -0.77
     millenn
    -0.74
    cipled
    -0.73
     dilig
    -0.71
     challeng
    -0.70
     enthusi
    -0.70
     gobl
    -0.69
     suspic
    -0.69
    POSITIVE LOGITS
     She
    2.50
    She
    2.34
     Her
    2.15
    she
    2.15
    Her
    2.07
     she
    2.05
     her
    1.99
     herself
    1.98
     SHE
    1.96
     HER
    1.69
    Act Density 0.478%

    No Known Activations