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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives that describe qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ockey
    -0.16
     Cypress
    -0.15
    realm
    -0.15
    .habbo
    -0.15
    ÑĪе
    -0.14
     Cove
    -0.14
    abaj
    -0.13
    aban
    -0.13
    /Branch
    -0.13
    èī¯
    -0.13
    POSITIVE LOGITS
    ç¬
    0.15
    uster
    0.15
    quot
    0.14
    .options
    0.14
    PCM
    0.13
     spéc
    0.13
    å¹¹
    0.13
    arer
    0.13
    echan
    0.13
    arness
    0.13
    Act Density 0.148%

    No Known Activations