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

    Neuronpedia

    INDEX
    Explanations

    references to narratives and storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poffe
    -0.69
     ſtate
    -0.69
     myſelf
    -0.68
     himſelf
    -0.67
     Efq
    -0.64
     anſ
    -0.63
    ſelf
    -0.63
     raiſ
    -0.62
     themſelves
    -0.62
     beschik
    -0.62
    POSITIVE LOGITS
     sneaking
    1.33
     sneak
    1.27
     inserted
    1.24
     sprinkled
    1.23
     mixed
    1.15
     incorporated
    1.14
     injected
    1.14
     slipped
    1.14
     crept
    1.14
     creeping
    1.12
    Act Density 0.429%

    No Known Activations