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

    Neuronpedia

    INDEX
    Explanations

    expressions related to honesty and intent in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoresizingMask
    -0.68
    principalColumn
    -0.66
    [++
    -0.64
    IntoConstraints
    -0.63
     архивлан
    -0.62
     Args
    -0.62
    uxxxx
    -0.61
    )++;
    -0.60
     Waray
    -0.60
     PopupWindow
    -0.60
    POSITIVE LOGITS
     sincere
    0.74
     earnest
    0.66
     sincerely
    0.62
    Honest
    0.58
     intenciones
    0.58
    incere
    0.58
     trying
    0.55
     intentions
    0.55
     honest
    0.53
     intenta
    0.52
    Act Density 0.349%

    No Known Activations