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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences framed or presented in a particular way

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "framing" in discussions or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onge
    -0.84
    ibaba
    -0.83
    adder
    -0.77
    withstanding
    -0.73
    raltar
    -0.72
    ergic
    -0.72
    bek
    -0.72
    Mos
    -0.71
    ggies
    -0.69
    ectar
    -0.68
    POSITIVE LOGITS
    eering
    1.12
     framed
    1.03
     framing
    0.92
     frames
    0.90
     Frames
    0.81
    eers
    0.79
     Frame
    0.73
     frame
    0.73
     Âł Âł Âł Âł Âł Âł Âł Âł
    0.71
     sunglasses
    0.70
    Act Density 0.010%

    No Known Activations