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

    Neuronpedia

    INDEX
    Explanations

    words related to making something stricter or less strict

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restriction and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ination
    -0.74
    melon
    -0.73
    iop
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
    riot
    -0.64
    inates
    -0.62
    ios
    -0.62
    è¦ļéĨĴ
    -0.62
    د
    -0.61
    lan
    -0.61
    POSITIVE LOGITS
    laus
    0.82
    hift
    0.81
     depreciation
    0.79
     dramatically
    0.74
     gears
    0.73
    imar
    0.72
     deepen
    0.72
     downwards
    0.72
     considerably
    0.72
     tightening
    0.71
    Act Density 0.038%

    No Known Activations