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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating potential outcomes or effects

    oai_token-act-pair · gpt-3.5-turbo

    critical situations or events that could lead to significant consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     requests
    -0.68
     appropriated
    -0.68
     tuned
    -0.66
     coefficients
    -0.66
    */(
    -0.65
     allocated
    -0.64
     observation
    -0.64
     impulses
    -0.64
     inputs
    -0.64
     faculties
    -0.63
    POSITIVE LOGITS
     doom
    1.14
     Armageddon
    0.97
     downfall
    0.93
     disastrous
    0.90
     havoc
    0.90
     engulf
    0.88
     bloodshed
    0.83
     ruin
    0.83
     fate
    0.81
     mayhem
    0.81
    Act Density 0.460%

    No Known Activations