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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or an unspecified idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elmet
    -0.17
    åĤ
    -0.15
    éis
    -0.14
    lz
    -0.14
    dou
    -0.14
    eller
    -0.14
    emble
    -0.14
    sey
    -0.14
    bler
    -0.14
    okol
    -0.13
    POSITIVE LOGITS
     else
    0.20
     that
    0.18
     we
    0.17
     which
    0.17
     ÑĤоÑĢ
    0.16
    ÙĮ
    0.15
     ÏĢοÏħ
    0.15
     worth
    0.15
    that
    0.15
    ksam
    0.15
    Act Density 0.023%

    No Known Activations