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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to negative or severe conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "severe" and related severity descriptors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atu
    -0.87
    wagen
    -0.81
    ynthesis
    -0.81
     Tycoon
    -0.77
    xxxxxxxx
    -0.76
    etts
    -0.76
    cellent
    -0.76
    raltar
    -0.74
    ilater
    -0.73
    kil
    -0.72
    POSITIVE LOGITS
     depressive
    0.87
     enough
    0.87
     repercussions
    0.87
     earthqu
    0.87
     understatement
    0.86
     punishments
    0.86
     consequences
    0.84
     severity
    0.84
     traumatic
    0.83
     punishment
    0.82
    Act Density 0.035%

    No Known Activations