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

    Neuronpedia

    INDEX
    Explanations

    elements related to anticipation or predictions about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.51
     explanation
    -0.48
    のに
    -0.48
    Erreferentziak
    -0.48
     toch
    -0.47
    sometimes
    -0.44
    ீர
    -0.44
     Saltar
    -0.44
    RenderAtEndOf
    -0.43
    paq
    -0.42
    POSITIVE LOGITS
     Hopefully
    1.35
    Hopefully
    1.33
     hopefully
    1.32
    hopefully
    1.27
     Expect
    1.21
     expect
    1.20
    Expect
    1.18
    Fingers
    1.14
    fingers
    1.00
     Fingers
    1.00
    Act Density 0.271%

    No Known Activations