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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or indecisiveness

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation or expressions of doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.84
    Interstitial
    -0.76
    ãĥ¯ãĥ³
    -0.75
    Buyable
    -0.71
    Desk
    -0.67
    è£ħ
    -0.66
    çĶ°
    -0.65
     Sabha
    -0.65
     Kap
    -0.64
    ESSION
    -0.64
    POSITIVE LOGITS
    âĢķ
    0.86
    £
    0.76
    ump
    0.76
    ¢
    0.74
    ĺ
    0.72
    ¼
    0.70
    Ķ
    0.70
    ¡
    0.69
    º
    0.67
    ¿
    0.66
    Act Density 0.329%

    No Known Activations