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

    Neuronpedia

    INDEX
    Explanations

    references to pockets and pocketed items

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    HttpMethod
    -0.91
     Catawiki
    -0.82
    thâu
    -0.77
    scriptcase
    -0.75
     Abp
    -0.75
     rospy
    -0.74
     Hemsworth
    -0.74
    quelize
    -0.74
     Réponses
    -0.74
     henvisninger
    -0.73
    POSITIVE LOGITS
     Pocket
    1.78
    Pocket
    1.78
     pocket
    1.76
    pocket
    1.66
     pockets
    1.63
     Pockets
    1.42
     bolsillo
    1.25
     bolsillos
    1.14
     poches
    1.10
    ポケット
    1.09
    Act Density 0.002%

    No Known Activations