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

    Neuronpedia

    INDEX
    Explanations

    phrases related to product features and operational ease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pac
    -0.16
    aliz
    -0.15
    pac
    -0.14
    ãģ¹ãģį
    -0.14
    Wrapped
    -0.14
    Malloc
    -0.14
    меÑĩ
    -0.14
    ongo
    -0.14
     wre
    -0.14
    avr
    -0.13
    POSITIVE LOGITS
     mechanism
    0.29
     mechanisms
    0.26
     fold
    0.25
    -fold
    0.24
     folding
    0.24
     retract
    0.23
     pneum
    0.23
     slides
    0.23
     slide
    0.21
     MANUAL
    0.21
    Act Density 0.182%

    No Known Activations