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

    Neuronpedia

    INDEX
    Explanations

    references to Hindu deities or associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arine
    -0.15
    clare
    -0.15
    292
    -0.15
    aleur
    -0.15
    avel
    -0.15
    à¥Ģà¤Ĩà¤Ī
    -0.14
    avin
    -0.14
    jos
    -0.14
     trusting
    -0.14
    urum
    -0.14
    POSITIVE LOGITS
    atab
    0.25
    akt
    0.24
    ri
    0.24
    aktiv
    0.23
    arda
    0.22
    ree
    0.21
    odash
    0.20
    astr
    0.20
    iva
    0.19
    ivar
    0.19
    Act Density 0.014%

    No Known Activations