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

    Neuronpedia

    INDEX
    Explanations

    words related to questions about specific details or information

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to societal issues and the factors surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.86
    NetMessage
    -0.84
    spread
    -0.81
    steamapps
    -0.75
    tyard
    -0.73
    ibaba
    -0.73
     Leban
    -0.72
    dden
    -0.71
    tesy
    -0.69
    vity
    -0.69
    POSITIVE LOGITS
     awaits
    0.75
     happens
    0.74
     determines
    0.69
     alloc
    0.69
     pans
    0.67
     they
    0.66
     you
    0.65
     holds
    0.64
     survives
    0.64
     deems
    0.63
    Act Density 0.128%

    No Known Activations