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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or attributes, such as names and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRD
    -0.15
    AREST
    -0.15
     addCriterion
    -0.14
     Bender
    -0.14
     gön
    -0.14
     kvin
    -0.14
    SED
    -0.14
    intl
    -0.14
    >NN
    -0.14
    ponsible
    -0.14
    POSITIVE LOGITS
    oco
    0.15
    arak
    0.15
    ara
    0.15
     Credits
    0.14
     Moms
    0.14
    12
    0.14
    âľ
    0.14
    ebi
    0.14
    _NEXT
    0.14
    xbf
    0.14
    Act Density 0.008%

    No Known Activations