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

    Neuronpedia

    INDEX
    Explanations

    phrases involving humorous or absurd situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adin
    -0.15
    Cipher
    -0.14
    andal
    -0.14
    adlo
    -0.14
    anden
    -0.14
    arel
    -0.14
    à¤ł
    -0.14
    andin
    -0.14
    ceptors
    -0.14
    trinsic
    -0.14
    POSITIVE LOGITS
     least
    0.17
    COPE
    0.15
    itchens
    0.15
    uki
    0.15
    poon
    0.14
    quete
    0.14
    ruit
    0.14
     Williamson
    0.14
    vice
    0.14
    殿
    0.14
    Act Density 0.455%

    No Known Activations