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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or topics in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to making observations or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uth
    -0.76
    )=(
    -0.73
    AU
    -0.73
    hers
    -0.72
    ingly
    -0.72
    oux
    -0.71
    ilyn
    -0.71
    thens
    -0.70
    Bind
    -0.69
    ieu
    -0.68
    POSITIVE LOGITS
     graphs
    0.87
     examples
    0.86
     datas
    0.81
     headlines
    0.81
     demographics
    0.80
     positives
    0.78
     diagram
    0.78
     history
    0.78
     similarities
    0.77
     diagrams
    0.77
    Act Density 0.221%

    No Known Activations