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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and events

    oai_token-act-pair · gpt-3.5-turbo

    historical figures and their relationships or lineage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icone
    -0.64
    safety
    -0.63
     bounce
    -0.61
     rollout
    -0.59
    Safety
    -0.58
    stakes
    -0.57
    healthy
    -0.56
     hassle
    -0.56
     DHS
    -0.54
    itivity
    -0.54
    POSITIVE LOGITS
     philosopher
    0.77
     histor
    0.75
     Ottoman
    0.75
     scholar
    0.72
     Britann
    0.71
     theolog
    0.70
     Athen
    0.68
     historian
    0.67
     colonial
    0.65
     1968
    0.65
    Act Density 3.321%

    No Known Activations