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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tagging and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ika
    -0.14
    airy
    -0.14
    aza
    -0.14
    ahu
    -0.14
    empo
    -0.14
    aves
    -0.14
     Duffy
    -0.13
    cases
    -0.13
    ouns
    -0.13
     hors
    -0.13
    POSITIVE LOGITS
     etc
    0.16
    pedo
    0.15
     Uncategorized
    0.15
    uento
    0.13
    infeld
    0.13
     Riley
    0.13
    ãĢĩ
    0.13
    ktop
    0.13
    abee
    0.13
    RITE
    0.13
    Act Density 0.053%

    No Known Activations