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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusion or reference to multiple entities or examples within a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رÙģØ©
    -0.14
    ãģ»ãģ©
    -0.14
    defs
    -0.14
    lý
    -0.14
    ÑīинÑĭ
    -0.14
    YYY
    -0.14
    \views
    -0.14
    ãģ°ãģĭãĤĬ
    -0.14
    uggage
    -0.13
    lite
    -0.13
    POSITIVE LOGITS
     others
    0.38
    others
    0.25
     Others
    0.25
     many
    0.24
    st
    0.23
    Others
    0.23
     пÑĢоÑĩ
    0.21
     else
    0.19
     them
    0.17
    t
    0.16
    Act Density 0.013%

    No Known Activations