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

    Neuronpedia

    INDEX
    Explanations

    mentions of law enforcement incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     resil
    -0.73
     cens
    -0.68
     arson
    -0.68
     Levant
    -0.68
     bombard
    -0.67
     dish
    -0.67
     corrections
    -0.67
     behavi
    -0.67
     redevelop
    -0.64
     shorth
    -0.64
    POSITIVE LOGITS
    fw
    1.15
    df
    1.12
    bm
    1.09
    zx
    1.07
    zn
    1.06
    bc
    1.04
    fb
    1.04
    cd
    1.03
    wb
    1.01
    gd
    0.97
    Act Density 0.050%

    No Known Activations