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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causal relationships and implications based on varying conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental impacts and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Phill
    -0.71
    afety
    -0.68
    usp
    -0.68
     Elijah
    -0.65
    stros
    -0.63
     unlaw
    -0.62
    akespe
    -0.61
     revocation
    -0.61
     disse
    -0.60
     particulars
    -0.60
    POSITIVE LOGITS
    than
    1.29
     healthier
    1.08
     fewer
    1.02
     richer
    1.00
    higher
    1.00
     decreased
    1.00
     quicker
    0.99
     faster
    0.98
     stronger
    0.97
    Decre
    0.96
    Act Density 1.101%

    No Known Activations