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

    Neuronpedia

    INDEX
    Explanations

    references to monsters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orte
    -0.16
    gang
    -0.16
    istry
    -0.15
    prus
    -0.15
    icts
    -0.15
    ãĥ³ãĥ
    -0.14
    DonaldTrump
    -0.14
    usa
    -0.14
    agher
    -0.14
     Lennon
    -0.14
    POSITIVE LOGITS
    ous
    0.22
    iem
    0.17
    lijke
    0.16
    ously
    0.16
    loff
    0.16
    liness
    0.15
    821
    0.15
    kad
    0.15
    owie
    0.15
    inth
    0.15
    Act Density 0.025%

    No Known Activations