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

    Neuronpedia

    INDEX
    Explanations

    prepositions that indicate movement or direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direction or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cape
    -0.74
     polled
    -0.70
    rated
    -0.69
    rating
    -0.68
    Edited
    -0.67
     tested
    -0.67
     inconsist
    -0.67
    code
    -0.65
     suscept
    -0.65
     hesitated
    -0.64
    POSITIVE LOGITS
     Dover
    0.87
     Auschwitz
    0.85
     adulthood
    0.85
     Mecca
    0.83
     downtown
    0.82
    ascus
    0.81
     Clarks
    0.81
     Bangkok
    0.80
    asted
    0.79
    iling
    0.78
    Act Density 0.239%

    No Known Activations