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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to severity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.55
     merciless
    -0.54
     makeStyles
    -0.53
     farlo
    -0.52
    DataBind
    -0.50
    شنایی
    -0.50
     désigner
    -0.49
     ddelweddau
    -0.49
     AdapterView
    -0.49
     ruthless
    -0.49
    POSITIVE LOGITS
    Horrible
    1.27
     hor
    1.21
     horrible
    1.20
     Hor
    1.19
     awful
    1.14
    hor
    1.13
     terrible
    1.05
    rible
    1.04
    Hor
    0.98
    terrible
    0.94
    Act Density 0.080%

    No Known Activations