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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions or concentrations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating restrictions or limitations on specific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.90
    natureconservancy
    -0.69
    oris
    -0.68
    CCC
    -0.65
    acter
    -0.63
    asc
    -0.63
    ++++
    -0.63
    acha
    -0.62
    assi
    -0.62
    shown
    -0.61
    POSITIVE LOGITS
     purely
    0.74
     superficial
    0.73
     limited
    0.72
     narrowly
    0.72
     sparing
    0.72
     bare
    0.70
     cosmetic
    0.69
     marginally
    0.67
    arde
    0.66
    oteric
    0.64
    Act Density 0.464%

    No Known Activations