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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a hypothetical scenario or outcome dependent on a specific condition being met or not

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     highlight
    -0.59
    interstitial
    -0.58
     Tick
    -0.55
    atile
    -0.55
    è¦ļéĨĴ
    -0.54
     undermines
    -0.54
     amuse
    -0.53
     brink
    -0.52
    Cube
    -0.52
     hilarious
    -0.52
    POSITIVE LOGITS
     stayed
    1.18
     been
    1.17
     waited
    1.13
    been
    1.08
     hadn
    1.06
     remained
    1.06
     gone
    1.05
     existed
    1.03
     gotten
    1.02
     survived
    1.00
    Act Density 0.076%

    No Known Activations