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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigations, legal issues, and controversial activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    witz
    -0.74
     Rudd
    -0.72
    ORTS
    -0.71
    ãģĨ
    -0.71
    swick
    -0.68
    ï¸ı
    -0.68
     Seah
    -0.67
     totality
    -0.67
    FUL
    -0.67
     spare
    -0.66
    POSITIVE LOGITS
    ocese
    1.39
    urnal
    1.34
    abol
    1.25
    abolic
    1.19
    agon
    1.11
    ablo
    1.07
    agram
    1.00
    plom
    0.98
    adem
    0.92
    aries
    0.90
    Act Density 0.010%

    No Known Activations