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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs related to asking questions or seeking information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AlterField
    -0.60
    Портал
    -0.58
     Sauber
    -0.57
    itudinal
    -0.57
    sterious
    -0.55
     GAP
    -0.53
    ership
    -0.52
    kegaard
    -0.52
    AttributeSet
    -0.52
    RepeatedField
    -0.51
    POSITIVE LOGITS
     Numerade
    0.75
     ferons
    0.68
     honte
    0.63
     rendel
    0.62
     المعيارى
    0.60
     beszél
    0.60
     larmes
    0.58
     répon
    0.57
     vostri
    0.56
     képes
    0.56
    Act Density 0.108%

    No Known Activations