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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recommendations or preferred options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kushner
    -0.17
    opsis
    -0.16
    ега
    -0.15
    Wunused
    -0.14
    обÑī
    -0.14
    UDO
    -0.14
    ádu
    -0.14
    adolu
    -0.13
     McMahon
    -0.13
    stants
    -0.13
    POSITIVE LOGITS
     place
    0.31
     to
    0.23
     choice
    0.22
     way
    0.21
    _place
    0.21
     Place
    0.21
    åİ»
    0.20
    -place
    0.20
     places
    0.19
     PLACE
    0.19
    Act Density 0.095%

    No Known Activations