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

    Neuronpedia

    INDEX
    Explanations

    sentences emphasizing immediate actions or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     guma
    -0.79
     pinak
    -0.62
     tanong
    -0.61
     loob
    -0.56
     kanya
    -0.54
     walang
    -0.54
     pama
    -0.53
     maraming
    -0.51
     essentiels
    -0.50
     ibang
    -0.50
    POSITIVE LOGITS
     immediate
    0.81
     immediately
    0.79
     Immediate
    0.78
     pamph
    0.77
     Immediately
    0.75
     IMMEDIATE
    0.74
    Immediately
    0.71
     immedi
    0.71
     dramatist
    0.70
    immediately
    0.69
    Act Density 0.101%

    No Known Activations