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

    Neuronpedia

    INDEX
    Explanations

    phrases and sentences describing actions or activities that involve movement or change of location

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and infinitive verbs indicating purpose or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    canon
    -0.77
     Definitions
    -0.76
     implication
    -0.74
     algorith
    -0.74
     defining
    -0.72
     Created
    -0.71
    cedented
    -0.71
     shaping
    -0.70
    binding
    -0.69
     predicting
    -0.68
    POSITIVE LOGITS
     evacuate
    1.46
     sleep
    1.33
     disembark
    1.32
     travel
    1.29
     stay
    1.29
     attend
    1.28
     roam
    1.23
     commute
    1.22
     eat
    1.21
     walk
    1.21
    Act Density 0.272%

    No Known Activations