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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "known"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iron
    -0.15
    odon
    -0.15
    ric
    -0.15
    obo
    -0.15
    RIC
    -0.15
    uelle
    -0.14
    esser
    -0.14
    vox
    -0.14
    دارÛĮ
    -0.14
    CLR
    -0.14
    POSITIVE LOGITS
    CEED
    0.15
     downt
    0.14
    lift
    0.14
    åºľ
    0.14
    cri
    0.14
    ТÐŀ
    0.14
    aghan
    0.13
    kest
    0.13
    olumn
    0.13
    _ABI
    0.13
    Act Density 0.008%

    No Known Activations