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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating possession or actions performed by characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "...
    -0.17
    owards
    -0.16
    ENTA
    -0.15
    sun
    -0.15
     hâl
    -0.15
     seper
    -0.14
     recieved
    -0.14
    ungan
    -0.14
     arte
    -0.14
     vale
    -0.14
    POSITIVE LOGITS
     _:
    0.17
     wrapped
    0.17
     Babies
    0.16
    wrapped
    0.15
     asleep
    0.14
    apyrus
    0.14
    .protocol
    0.14
     Pediatric
    0.13
     overnight
    0.13
     secrecy
    0.13
    Act Density 0.000%

    No Known Activations