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

    Neuronpedia

    INDEX
    Explanations

    instances of factual statements and descriptions of specific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /GPL
    -0.17
    enk
    -0.16
    sip
    -0.15
    _ASSUME
    -0.15
    rowable
    -0.15
    lsru
    -0.14
    мага
    -0.14
    coe
    -0.14
    reten
    -0.14
    objc
    -0.14
    POSITIVE LOGITS
     brid
    0.15
     def
    0.15
     Alt
    0.15
    arpa
    0.14
     bet
    0.14
    uka
    0.14
     fore
    0.14
     deg
    0.13
    enta
    0.13
    uly
    0.13
    Act Density 0.947%

    No Known Activations