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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obstruction or concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ্ষ
    -0.53
    ctrica
    -0.47
    setVerticalGroup
    -0.46
     address
    -0.45
     both
    -0.45
     sandalias
    -0.45
     ==
    -0.43
    сту
    -0.42
    ==
    -0.42
     sirena
    -0.42
    POSITIVE LOGITS
    +#+#
    0.79
    ThroughAttribute
    0.77
     HasFactory
    0.75
    StoreMessageInfo
    0.70
     concealment
    0.70
    hyrchwyd
    0.69
     للمعارف
    0.67
     shadow
    0.66
    ProgressHUD
    0.66
    Soorten
    0.64
    Act Density 0.209%

    No Known Activations