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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to engineering, manufacturing, and industrial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.02
    2:0.07
    3:0.26
    4:0.02
    5:0.18
    6:0.02
    7:0.08
    8:0.03
    9:0.02
    10:0.14
    11:0.02
    Negative Logits
    nesday
    -1.84
     Unsure
    -1.81
    ontent
    -1.79
    utenberg
    -1.76
     stumble
    -1.74
     blindly
    -1.74
    someone
    -1.73
    isky
    -1.69
    jri
    -1.69
    umblr
    -1.68
    POSITIVE LOGITS
    ®,
    2.24
     cures
    2.04
     suspensions
    1.94
     replacements
    1.93
     products
    1.89
     warships
    1.88
     powd
    1.87
     medicines
    1.87
    ®
    1.87
     vaccines
    1.83
    Act Density 0.140%

    No Known Activations