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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or hope regarding outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.18
    idas
    -0.15
     erg
    -0.14
    oley
    -0.14
    atis
    -0.14
    alian
    -0.14
     ost
    -0.14
    aved
    -0.14
    âr
    -0.14
    rb
    -0.14
    POSITIVE LOGITS
     yesterday
    0.16
    abbr
    0.14
    ugu
    0.14
    æĺ¨
    0.14
    atego
    0.14
    à¸Ħำ
    0.13
    Originally
    0.13
    BOVE
    0.13
    Stamped
    0.13
    GRES
    0.13
    Act Density 0.363%

    No Known Activations