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

    Neuronpedia

    INDEX
    Explanations

    phrases related to putting someone or something in a specific position or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prioritizing individuals or groups in a systemic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.72
     summar
    -0.65
    TAIN
    -0.64
     partName
    -0.63
    merce
    -0.62
     respondents
    -0.62
    nesday
    -0.62
     Mondays
    -0.60
    ecd
    -0.60
     Documentation
    -0.60
    POSITIVE LOGITS
     pedest
    0.86
     brink
    0.82
     equation
    0.74
     fold
    0.67
    competitive
    0.66
     embrace
    0.65
    =~=~
    0.65
     cruc
    0.64
     safe
    0.64
     afterlife
    0.64
    Act Density 0.512%

    No Known Activations