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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating hypothetical situations or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apparently
    -0.64
    seamnă
    -0.62
     Apparently
    -0.62
     paraît
    -0.62
    Apparently
    -0.61
     apparently
    -0.60
    DataAnnotations
    -0.58
     verkar
    -0.57
     reportedly
    -0.57
     sembler
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
     belonged
    0.63
    hearsed
    0.60
    InvalidProtocol
    0.55
    esterday
    0.55
     autorytatywna
    0.55
    ftagPool
    0.54
     belong
    0.54
    agisse
    0.53
     المعيارى
    0.53
    Act Density 0.114%

    No Known Activations