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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or action

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to movement or driving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     immersion
    -0.68
    reements
    -0.62
     dermat
    -0.59
     Plastic
    -0.59
     senses
    -0.59
     contingency
    -0.58
     Flavoring
    -0.58
     palate
    -0.57
     dé
    -0.56
     Permanent
    -0.56
    POSITIVE LOGITS
     towards
    1.19
     toward
    1.19
     away
    1.10
     onwards
    1.08
     through
    1.06
     uphill
    1.02
     along
    0.99
     ahead
    0.98
     across
    0.97
     alongside
    0.94
    Act Density 0.186%

    No Known Activations