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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating confidence or strong beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RTDA
    -0.52
    IBOutlet
    -0.51
     שוליים
    -0.50
    IsPostBack
    -0.45
    TagMode
    -0.45
     Winaray
    -0.41
     nemici
    -0.40
     bum
    -0.40
     AssemblyProduct
    -0.39
    tonsoft
    -0.39
    POSITIVE LOGITS
     prioriti
    0.73
     keen
    0.70
     sat
    0.66
     paraly
    0.64
     organising
    0.53
    Whilst
    0.53
     stood
    0.53
     gutted
    0.52
     resident
    0.51
     specialising
    0.51
    Act Density 0.279%

    No Known Activations