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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to friendliness and a welcoming atmosphere

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.18
    Ìĥ
    -0.17
    ngo
    -0.17
    .scalablytyped
    -0.14
    ilion
    -0.14
    viz
    -0.14
    ilda
    -0.14
    lette
    -0.14
    igon
    -0.14
    neau
    -0.14
    POSITIVE LOGITS
    ness
    0.19
    lest
    0.17
    weise
    0.16
    ities
    0.16
    uzzer
    0.16
    zsche
    0.16
    -looking
    0.15
    yyyy
    0.15
    าà¸ģร
    0.15
     enough
    0.15
    Act Density 0.027%

    No Known Activations