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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BrowserModule
    -0.72
    complexContent
    -0.65
    MLLoader
    -0.61
    setDo
    -0.57
     vPvB
    -0.55
    RefNanny
    -0.55
    DockStyle
    -0.55
    HideFlags
    -0.54
     PropTypes
    -0.53
    bewerken
    -0.52
    POSITIVE LOGITS
     comes
    0.69
     are
    0.67
    with
    0.67
     Comes
    0.66
    fordshire
    0.64
    inafter
    0.64
     goes
    0.63
     ende
    0.62
     come
    0.60
     we
    0.59
    Act Density 0.114%

    No Known Activations