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

    Neuronpedia

    INDEX
    Explanations

    themes related to social critique and imagination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oya
    -0.16
    Äįel
    -0.16
    çľī
    -0.15
    llum
    -0.14
    weis
    -0.14
    itives
    -0.13
    wis
    -0.13
    iren
    -0.13
    ascus
    -0.13
     perplex
    -0.13
    POSITIVE LOGITS
     imagine
    0.62
     imag
    0.61
     imagination
    0.56
     Imagine
    0.54
     picture
    0.54
    imag
    0.53
     imaging
    0.52
     Imag
    0.52
    Imagine
    0.51
     imagining
    0.51
    Act Density 0.337%

    No Known Activations