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

    Neuronpedia

    INDEX
    Explanations

    mentions of police actions or law enforcement situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.37
     FLORIDA
    -0.35
     Florida
    -0.34
     marins
    -0.34
     Cairo
    -0.33
     tetra
    -0.32
    Florida
    -0.32
     phosphory
    -0.32
     German
    -0.31
    bav
    -0.30
    POSITIVE LOGITS
     Manipur
    0.99
     Naga
    0.73
     Manip
    0.73
    
    0.72
     Assam
    0.68
    wahati
    0.65
     Tripura
    0.65
     manip
    0.63
     <<<<<<<<<<<<<<
    0.63
     Dima
    0.63
    Act Density 0.072%

    No Known Activations