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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal identity and character development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abandonment
    -0.14
     postpon
    -0.13
     indifference
    -0.13
     NEGLIGENCE
    -0.13
     delaying
    -0.13
     detached
    -0.13
     pard
    -0.12
     exem
    -0.12
     dismissing
    -0.12
     invalidate
    -0.12
    POSITIVE LOGITS
     restriction
    0.81
     restrictions
    0.78
     restricted
    0.77
     limitation
    0.72
    restrict
    0.71
     limitations
    0.71
     restrict
    0.70
    éĻIJåĪ¶
    0.70
    restriction
    0.69
    restricted
    0.66
    Act Density 0.723%

    No Known Activations