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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions and decisions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    yrinth
    -0.74
    glers
    -0.70
    intendent
    -0.64
     %%
    -0.58
     surpr
    -0.57
     HERE
    -0.54
    pmwiki
    -0.53
     Lands
    -0.53
     Marketplace
    -0.51
     Maritime
    -0.50
    POSITIVE LOGITS
     himself
    1.01
    thood
    0.84
     herself
    0.77
     his
    0.68
     someday
    0.68
     girlfriend
    0.66
     teammates
    0.61
    his
    0.59
     anymore
    0.58
    ¶æ
    0.57
    Act Density 0.892%

    No Known Activations