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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "delve" and variations of the word "ving", indicating a focus on exploration or deep investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olph
    -0.17
    nelle
    -0.17
    -gnu
    -0.15
    à¥įà¤ł
    -0.15
    therapy
    -0.14
    .reserve
    -0.14
    atorio
    -0.14
    nio
    -0.14
    lit
    -0.14
    Å¡ak
    -0.14
    POSITIVE LOGITS
    IOS
    0.15
    ιδ
    0.15
    essler
    0.14
    oppins
    0.14
    æº
    0.14
    ottes
    0.13
    ertil
    0.13
     Kang
    0.13
    rott
    0.13
     registrazione
    0.13
    Act Density 0.004%

    No Known Activations