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

    Neuronpedia

    INDEX
    Explanations

    references to mailing addresses and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asset
    -0.17
     æ¬
    -0.15
    osit
    -0.15
    assel
    -0.14
    inges
    -0.14
    kaar
    -0.14
    é¡
    -0.14
    ella
    -0.14
    æª
    -0.14
    bero
    -0.14
    POSITIVE LOGITS
     attn
    0.16
    .Unit
    0.16
     Unit
    0.15
    nore
    0.15
     Attention
    0.14
    ÑĢава
    0.14
    lash
    0.14
    SimpleName
    0.14
    oram
    0.13
     attention
    0.13
    Act Density 0.023%

    No Known Activations