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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with temptation and enticement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.21
    uster
    -0.15
    Ấ
    -0.15
    uez
    -0.14
    omat
    -0.14
    shirt
    -0.14
    shaw
    -0.14
    uale
    -0.13
    uent
    -0.13
    eci
    -0.13
    POSITIVE LOGITS
    Pub
    0.15
    ãĥĭãĤ¢
    0.15
    aptop
    0.14
    ãĥĭãĥ¼
    0.14
    tempt
    0.14
    ehir
    0.14
    Äįin
    0.14
    gnu
    0.14
     tempting
    0.13
    اÙĦص
    0.13
    Act Density 0.037%

    No Known Activations