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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negation or absence

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and expressions of past actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antioxid
    -0.91
     portfolios
    -0.68
    BP
    -0.66
    ettlement
    -0.60
    redients
    -0.60
    ortment
    -0.59
    dan
    -0.59
     portfolio
    -0.58
    DIT
    -0.58
     SetTextColor
    -0.57
    POSITIVE LOGITS
    theless
    1.02
     nor
    0.98
     dime
    0.85
     EVER
    0.81
     dreamed
    0.79
    Initialized
    0.79
    rences
    0.76
     slightest
    0.72
    before
    0.71
    javascript
    0.70
    Act Density 0.164%

    No Known Activations