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

    Neuronpedia

    INDEX
    Explanations

    quotes and dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dain
    -0.19
    aad
    -0.18
     Leban
    -0.15
    dal
    -0.15
     оÑĩ
    -0.14
    ůsob
    -0.14
    oux
    -0.14
    KER
    -0.13
    -game
    -0.13
     control
    -0.13
    POSITIVE LOGITS
    regor
    0.15
    _itr
    0.14
    ledge
    0.13
     Doub
    0.13
     Maritime
    0.13
    liÄŁe
    0.13
    ebb
    0.13
     ÑĩеÑģ
    0.13
    ForEach
    0.13
     Serious
    0.13
    Act Density 0.058%

    No Known Activations