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

    Neuronpedia

    INDEX
    Explanations

    locations or objects related to storage or containment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of physical locations and objects within those settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isites
    -0.76
    akings
    -0.75
     Flavoring
    -0.74
     Parties
    -0.69
    blems
    -0.68
     penalties
    -0.67
     positives
    -0.67
     sexes
    -0.67
    Ps
    -0.67
     punishments
    -0.65
    POSITIVE LOGITS
     overlooking
    1.01
     surrounded
    0.94
    robe
    0.89
     somewhere
    0.88
     riddled
    0.87
     littered
    0.86
     courtyard
    0.84
     resembling
    0.83
     adorned
    0.80
     balcony
    0.79
    Act Density 0.252%

    No Known Activations