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

    Neuronpedia

    INDEX
    Explanations

    words related to current events and political situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ires
    -0.76
    ETS
    -0.69
    ocracy
    -0.68
     Pony
    -0.64
    ocratic
    -0.62
    efer
    -0.60
    estro
    -0.59
    ocrats
    -0.58
    eval
    -0.57
    onday
    -0.57
    POSITIVE LOGITS
    chard
    1.62
    acle
    1.49
    acles
    1.46
    Else
    1.43
    nam
    1.42
    ifice
    1.39
    chid
    1.38
    acular
    1.37
     alternatively
    1.34
     else
    1.24
    Act Density 2.000%

    No Known Activations