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

    Neuronpedia

    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to locations and places to go or be

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requires
    -0.75
     Truman
    -0.66
     warrants
    -0.63
     batches
    -0.62
    UTH
    -0.62
     Beats
    -0.62
     RELE
    -0.61
     Causes
    -0.60
     implications
    -0.58
     scares
    -0.58
    POSITIVE LOGITS
     reside
    0.86
    ocate
    0.83
     refuge
    0.81
     dwell
    0.80
     pray
    0.80
     discuss
    0.78
     communicate
    0.77
     belong
    0.77
    ezvous
    0.76
     worship
    0.75
    Act Density 0.115%

    No Known Activations