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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forceful actions or destruction

    oai_token-act-pair · gpt-3.5-turbo

    actions associated with physical forces and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ende
    -0.72
    uben
    -0.68
    è¦ļéĨĴ
    -0.67
    ffe
    -0.67
    obbies
    -0.67
    ****************
    -0.63
    TPP
    -0.63
    enhagen
    -0.62
    morph
    -0.60
    Legal
    -0.60
    POSITIVE LOGITS
     away
    1.23
     apart
    1.02
     down
    1.00
     them
    1.00
     off
    0.95
     attackers
    0.92
     opponents
    0.88
     out
    0.88
     downward
    0.88
     forth
    0.87
    Act Density 0.230%

    No Known Activations