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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing dissatisfaction or criticism

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and other forms of the word "mean."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.89
    è¦ļéĨĴ
    -0.82
    ãĤ³
    -0.75
     GEAR
    -0.73
    ideo
    -0.71
    ARGET
    -0.70
    inations
    -0.70
    Miller
    -0.70
    DERR
    -0.69
    mie
    -0.68
    POSITIVE LOGITS
    etheless
    0.80
    aning
    0.79
    onymous
    0.79
    ragon
    0.77
    atos
    0.75
    roman
    0.71
    orf
    0.70
     effic
    0.70
    opter
    0.68
    entimes
    0.68
    Act Density 0.010%

    No Known Activations