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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to making something stricter or more secure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of regulation or restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agne
    -0.76
    ULT
    -0.73
     Americas
    -0.68
     Marathon
    -0.67
     Glory
    -0.66
    rum
    -0.66
     Carbuncle
    -0.65
    auri
    -0.65
    mits
    -0.65
     Columb
    -0.64
    POSITIVE LOGITS
     tightening
    1.33
     tightened
    1.23
     tighten
    1.11
     easing
    0.99
     tighter
    0.94
     undermin
    0.93
     tension
    0.92
     gau
    0.90
     throttle
    0.89
     clamp
    0.88
    Act Density 0.010%

    No Known Activations