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

    Neuronpedia

    INDEX
    Explanations

    numbers related to percentages and quantities

    oai_token-act-pair · gpt-3.5-turbo

    financial statistics and data related to resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norn
    -0.76
     Saying
    -0.70
     challeng
    -0.69
    epad
    -0.69
     Powerful
    -0.63
    bart
    -0.62
    pelling
    -0.58
     Shooter
    -0.58
     tremend
    -0.57
     Stamp
    -0.56
    POSITIVE LOGITS
     revolves
    1.27
     derives
    1.25
     resides
    1.25
     stems
    1.22
     eman
    1.16
     hinges
    1.14
     rests
    1.13
     consists
    1.13
     belongs
    1.12
     comes
    1.12
    Act Density 0.269%

    No Known Activations