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

    Neuronpedia

    INDEX
    Explanations

    legal terms and phrases related to offenses and defenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.60
     horrible
    -0.56
     everyone
    -0.52
     terrible
    -0.52
     everybody
    -0.49
     awful
    -0.49
     bad
    -0.48
     overworked
    -0.48
    ya
    -0.48
     little
    -0.48
    POSITIVE LOGITS
    findpost
    1.11
     Мексичка
    0.89
    WriteTagHelper
    0.89
     fubject
    0.88
    ]--;
    0.86
     perfons
    0.83
     '\\;'
    0.82
     (§
    0.82
    ^(@)
    0.81
     photolibrary
    0.79
    Act Density 1.392%

    No Known Activations