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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to situations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terrible things and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    큼
    -0.65
     pout
    -0.65
    Dolphin
    -0.63
    mlink
    -0.61
    躇
    -0.60
    iibo
    -0.59
     Bookmark
    -0.58
     surfboard
    -0.57
    Mango
    -0.57
     Bouquet
    -0.57
    POSITIVE LOGITS
    terrible
    1.63
     terrible
    1.62
     Terrible
    1.50
    Terrible
    1.42
     horrible
    1.21
     awful
    1.16
    awful
    1.00
     terribly
    0.94
    Horrible
    0.92
    rible
    0.91
    Act Density 0.003%

    No Known Activations