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

    Neuronpedia

    INDEX
    Explanations

    references to images and photo credits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olic
    -0.16
    lops
    -0.16
    ands
    -0.15
    rug
    -0.14
    rava
    -0.14
     Progress
    -0.14
     Sell
    -0.14
     proper
    -0.14
     ejected
    -0.14
    illis
    -0.13
    POSITIVE LOGITS
     Fra
    0.22
     Wire
    0.22
    Wire
    0.21
    Fra
    0.18
     Everett
    0.17
     Warner
    0.16
     Bang
    0.16
     wire
    0.15
    Splash
    0.15
    Universal
    0.15
    Act Density 0.014%

    No Known Activations