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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions taken without authorization or consent

    oai_token-act-pair · gpt-3.5-turbo

    references to lack of consent or knowledge in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.90
    ãĥĩ
    -0.83
    renheit
    -0.73
    çĶ°
    -0.71
    ardless
    -0.69
    çī
    -0.69
    ãĥ´
    -0.68
    ques
    -0.68
    Rate
    -0.67
     Rates
    -0.67
    POSITIVE LOGITS
     permission
    1.12
     assistance
    1.10
     intervention
    1.09
     supervision
    1.08
     consent
    1.07
     interruption
    1.02
     slightest
    0.99
     knowledge
    0.98
     accompan
    0.98
     aid
    0.96
    Act Density 0.109%

    No Known Activations