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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hierarchical relationships or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.86
     The
    -0.67
    The
    -0.63
     City
    -0.54
    MemoryWarning
    -0.53
     their
    -0.49
     New
    -0.49
     את
    -0.49
     H
    -0.48
     K
    -0.48
    POSITIVE LOGITS
    NameInMap
    0.90
     itſelf
    0.86
     doubtnut
    0.85
    Geplaatst
    0.82
    Hochspringen
    0.82
    contentLoaded
    0.79
     myſelf
    0.77
     hinweg
    0.77
    انجليز
    0.74
    IsContent
    0.74
    Act Density 0.505%

    No Known Activations