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

    Neuronpedia

    INDEX
    Explanations

    words related to trademarks or registered marks

    oai_token-act-pair · gpt-3.5-turbo

    words related to traditional practices or conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gur
    -0.69
    IRO
    -0.68
    ··
    -0.66
     overflow
    -0.65
     Bakr
    -0.64
     Younger
    -0.64
    asper
    -0.62
     straw
    -0.60
    9999
    -0.60
     Salman
    -0.59
    POSITIVE LOGITS
    itionally
    1.44
    emark
    1.38
    itional
    1.12
    eport
    1.11
    itions
    1.08
    ename
    1.08
    uctor
    1.08
    etooth
    1.04
    eways
    1.03
    uction
    1.02
    Act Density 0.015%

    No Known Activations