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

    Neuronpedia

    INDEX
    Explanations

    detailed information related to political and social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    osc
    -0.61
    ||||
    -0.59
    neg
    -0.57
    ãĤī
    -0.56
    Ùĩ
    -0.56
    /#
    -0.55
    roads
    -0.55
    ãģł
    -0.55
    thro
    -0.55
    eur
    -0.55
    POSITIVE LOGITS
    bestos
    1.42
    piring
    1.34
    semb
    1.29
    phalt
    1.28
    pects
    1.26
    ylum
    1.23
    piration
    1.20
    semble
    1.13
    king
    1.09
    ymm
    1.08
    Act Density 0.409%

    No Known Activations