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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stupid" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abstractmethod
    -0.66
     trattano
    -0.55
    <tbody>
    -0.54
    otex
    -0.53
    chos
    -0.51
    tah
    -0.50
    stru
    -0.50
    PreferredItem
    -0.49
    wlan
    -0.48
    zow
    -0.47
    POSITIVE LOGITS
    
    0.94
     dumb
    0.91
    dumb
    0.84
    stupid
    0.78
     stupid
    0.77
     Stupid
    0.77
    ambilan
    0.72
     Covington
    0.70
    brainly
    0.68
     stupidity
    0.68
    Act Density 0.070%

    No Known Activations