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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with blessings and positive acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsing
    -0.17
    ivate
    -0.15
    fty
    -0.14
    .Middle
    -0.14
    باÙĨ
    -0.14
    ãĤ¤ãĤ¯
    -0.14
    zin
    -0.14
    gy
    -0.14
    efs
    -0.14
    bes
    -0.14
    POSITIVE LOGITS
    ings
    0.20
    edly
    0.18
    ened
    0.17
    INGS
    0.17
    endale
    0.17
    esse
    0.15
    ificados
    0.15
    urar
    0.15
    ë°Ľ
    0.14
     ******************************************************************************↵
    0.14
    Act Density 0.016%

    No Known Activations