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

    Neuronpedia

    INDEX
    Explanations

    terms related to features and specifications of products or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.06
    3:0.41
    4:0.04
    5:0.07
    6:0.04
    7:0.05
    8:0.04
    9:0.03
    10:0.08
    11:0.05
    Negative Logits
     ­
    -2.48
     disgruntled
    -2.27
     mistaken
    -2.26
     alarmed
    -2.20
     outraged
    -2.15
     vehement
    -2.12
    licted
    -2.11
     unwittingly
    -2.09
     resent
    -2.08
     worried
    -2.07
    POSITIVE LOGITS
     addon
    2.13
    RPG
    2.12
     plugin
    2.11
     Simulator
    2.10
    osaurus
    2.09
     cube
    2.04
    hack
    2.04
    Mech
    2.04
    starter
    2.04
     Texture
    2.01
    Act Density 1.612%

    No Known Activations