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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forces or enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to any form of "force" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     board
    -0.71
    seys
    -0.67
    pty
    -0.66
    sey
    -0.63
     Kickstarter
    -0.60
    atur
    -0.60
     behold
    -0.60
    ̶
    -0.60
     Rosenstein
    -0.59
    oscope
    -0.58
    POSITIVE LOGITS
    force
    0.89
    ments
    0.84
    iencies
    0.83
    forcing
    0.77
    mson
    0.71
    ault
    0.70
     Awakens
    0.68
    lear
    0.68
    Thor
    0.67
    disabled
    0.66
    Act Density 0.017%

    No Known Activations