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

    Neuronpedia

    INDEX
    Explanations

    details of incidents involving violent conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unison
    -0.62
    selves
    -0.62
    yrinth
    -0.62
     Regist
    -0.61
    immers
    -0.57
    bnb
    -0.57
    glers
    -0.57
    eps
    -0.56
    %%
    -0.55
    hub
    -0.54
    POSITIVE LOGITS
     himself
    1.20
     his
    0.81
     persona
    0.80
     personally
    0.78
     wife
    0.74
     girlfriend
    0.73
     solitude
    0.66
     Himself
    0.66
     subordinates
    0.65
     onstage
    0.65
    Act Density 1.145%

    No Known Activations