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

    Neuronpedia

    INDEX
    Explanations

    expressions of desires or intentions related to being or doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.18
    ñana
    -0.15
    rea
    -0.15
    ÑĢана
    -0.15
    llib
    -0.15
    ừa
    -0.14
    ajar
    -0.14
    ilian
    -0.14
    anja
    -0.14
    inati
    -0.14
    POSITIVE LOGITS
    à¹Īà¸Ńย
    0.16
    tü
    0.15
    Eb
    0.14
    -fashioned
    0.14
    IALOG
    0.13
    ê·¹
    0.13
    eda
    0.13
    eb
    0.13
    orro
    0.13
     THINK
    0.13
    Act Density 0.012%

    No Known Activations