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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority or decision-making power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discretion and flexibility in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fever
    -0.80
     âĻ
    -0.73
     Mehran
    -0.70
    sov
    -0.69
     Mour
    -0.69
     Garfield
    -0.68
     Norn
    -0.68
    á
    -0.68
    onic
    -0.67
    Adams
    -0.67
    POSITIVE LOGITS
     discretion
    1.21
    retion
    1.01
     margin
    0.79
    ately
    0.78
     judgement
    0.75
     drawer
    0.75
     overr
    0.74
    awaru
    0.73
     calcul
    0.73
     derog
    0.72
    Act Density 0.008%

    No Known Activations