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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating predictions or expectations about future events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adb
    -0.15
    Indented
    -0.15
    insky
    -0.15
    argar
    -0.14
    _epochs
    -0.14
    .internet
    -0.14
    اÙĩ
    -0.14
    å£ĵ
    -0.14
    etten
    -0.14
    umba
    -0.14
    POSITIVE LOGITS
    ly
    0.19
    batis
    0.17
     Expected
    0.17
     fore
    0.17
    nost
    0.16
    (Expected
    0.16
    cka
    0.15
     Zus
    0.15
    çijŁ
    0.14
    QS
    0.14
    Act Density 0.018%

    No Known Activations