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

    Neuronpedia

    INDEX
    Explanations

    references to humanity as a collective group or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to humanity or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agall
    -0.67
    PM
    -0.66
    RECT
    -0.66
     Gillespie
    -0.66
    raph
    -0.65
     Fitzgerald
    -0.63
    roller
    -0.63
     Comprehensive
    -0.63
     Buckingham
    -0.62
    paragraph
    -0.62
    POSITIVE LOGITS
     beings
    1.11
    ankind
    1.02
     endowed
    0.85
     enslaved
    0.81
    zee
    0.79
     flourishing
    0.79
     inhab
    0.76
    itar
    0.76
    zees
    0.75
     extinct
    0.72
    Act Density 0.057%

    No Known Activations