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

    Neuronpedia

    INDEX
    Explanations

    sentences describing legal actions and sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¤
    -0.71
    edia
    -0.66
    âĹ¼
    -0.64
    verified
    -0.63
    mom
    -0.61
    atically
    -0.61
    Near
    -0.61
    events
    -0.60
    editor
    -0.60
     scouts
    -0.60
    POSITIVE LOGITS
     prison
    1.22
     jail
    1.14
     imprisonment
    1.13
     confinement
    1.09
     probation
    1.04
     incarceration
    1.04
     Detention
    1.03
    prison
    0.99
     incarcer
    0.98
     detention
    0.97
    Act Density 0.135%

    No Known Activations