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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or emphasis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Edit
    -0.95
    Versions
    -0.81
    edit
    -0.74
    uin
    -0.74
    effects
    -0.73
    alks
    -0.73
    intent
    -0.72
    achu
    -0.71
    AIDS
    -0.70
    someone
    -0.68
    POSITIVE LOGITS
     reminder
    1.19
     tad
    1.14
     testament
    1.09
     lot
    1.09
     bit
    1.08
     boon
    1.07
     fixture
    1.06
     distraction
    1.05
     nuisance
    1.05
     reflection
    1.04
    Act Density 1.272%

    No Known Activations