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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to imprisonment and legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -1.01
     guiActiveUnfocused
    -0.84
     grapes
    -0.82
    к
    -0.81
    natureconservancy
    -0.80
    omorphic
    -0.78
    é¾įåĸļ士
    -0.77
    itiveness
    -0.74
    phrine
    -0.72
    姫
    -0.71
    POSITIVE LOGITS
     Detention
    1.07
     Sergeant
    0.92
     detention
    0.90
     jailed
    0.87
     interrogated
    0.85
     sentenced
    0.84
     Guantanamo
    0.83
     interrogation
    0.82
     psychiatric
    0.82
     convicted
    0.81
    Act Density 0.527%

    No Known Activations