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

    Neuronpedia

    INDEX
    Explanations

    references to physical landmarks and their characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases related to natural landscapes and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Correct
    -0.82
    ospons
    -0.79
     Factors
    -0.73
    Interview
    -0.71
    Specifically
    -0.70
    Question
    -0.70
     Specifically
    -0.69
     Evaluation
    -0.69
    ONSORED
    -0.69
    endment
    -0.67
    POSITIVE LOGITS
     throb
    1.01
     gle
    0.95
     endless
    0.93
     wretched
    0.90
     towering
    0.90
     trem
    0.89
     frantic
    0.89
     innumerable
    0.89
     incess
    0.86
     ooz
    0.86
    Act Density 1.408%

    No Known Activations