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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to stewardship and responsible management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĢ«
    -0.16
    sci
    -0.15
    AI
    -0.15
    Offsets
    -0.14
    orf
    -0.14
    orris
    -0.14
    =forms
    -0.14
    arih
    -0.14
    ugi
    -0.14
    ction
    -0.13
    POSITIVE LOGITS
     Hanson
    0.15
    yas
    0.15
     extr
    0.15
    riz
    0.14
    _eg
    0.14
    777
    0.14
     Extr
    0.14
     discre
    0.14
    ampton
    0.14
    bara
    0.13
    Act Density 0.004%

    No Known Activations