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

    Neuronpedia

    INDEX
    Explanations

    phrases related to saving or preserving something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sclerosis
    -0.65
    SPONSORED
    -0.63
    ç«
    -0.61
    naire
    -0.60
    kt
    -0.59
    hole
    -0.59
    oun
    -0.58
    secution
    -0.58
    Rush
    -0.58
     Ascend
    -0.57
    POSITIVE LOGITS
     lives
    0.85
     Lives
    0.83
    Save
    0.81
     souls
    0.74
    Instance
    0.73
    éĹĺ
    0.71
     Saving
    0.71
    saving
    0.67
    osit
    0.66
     Sanctuary
    0.65
    Act Density 0.676%

    No Known Activations