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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.71
     chi̍t
    -0.70
     pinulongan
    -0.69
    SuccessListener
    -0.63
    TestBed
    -0.61
    RenderAtEndOf
    -0.61
    ChildScrollView
    -0.55
    antMatchers
    -0.54
     indisponible
    -0.54
    AndUpdate
    -0.53
    POSITIVE LOGITS
     uncommon
    0.84
     unusual
    0.72
     surprising
    0.71
     something
    0.66
     unheard
    0.65
     rocket
    0.63
     without
    0.62
     inusual
    0.59
     ungewöhn
    0.55
     helping
    0.54
    Act Density 0.290%

    No Known Activations