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

    Neuronpedia

    INDEX
    Explanations

    verbs related to increasing or intensifying action or production

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to increasing intensity or escalation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.76
    gee
    -0.74
     mate
    -0.71
    atron
    -0.69
    mates
    -0.69
     mates
    -0.65
    ocene
    -0.65
    acea
    -0.65
    士
    -0.65
    acle
    -0.64
    POSITIVE LOGITS
     vigilance
    0.99
     hostilities
    0.98
     pressure
    0.95
     urgency
    0.95
     scrutiny
    0.92
     awareness
    0.90
     lobbying
    0.87
     preparations
    0.87
     surveillance
    0.86
     secrecy
    0.83
    Act Density 0.229%

    No Known Activations