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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to behaviors or traits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     yourselves
    -0.68
    ulla
    -0.65
     oneself
    -0.64
    zens
    -0.61
    common
    -0.60
     CPC
    -0.60
    xious
    -0.58
     Barg
    -0.58
     ourselves
    -0.58
    GC
    -0.58
    POSITIVE LOGITS
     notwithstanding
    0.95
     shines
    0.90
     shone
    0.88
     coincide
    0.86
     contrasted
    0.85
     coupled
    0.84
     proved
    0.81
     belie
    0.81
     consisted
    0.80
     inspires
    0.79
    Act Density 0.279%

    No Known Activations