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

    Neuronpedia

    INDEX
    Explanations

    patterns or formats in the text that resemble examples or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.22
    3:0.11
    4:0.10
    5:0.03
    6:0.06
    7:0.15
    8:0.04
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
     predators
    -1.64
     bodies
    -1.64
     disciplines
    -1.64
     distractions
    -1.63
    ading
    -1.61
     instruments
    -1.60
     emergencies
    -1.51
     detectors
    -1.43
    isi
    -1.43
     sacrific
    -1.42
    POSITIVE LOGITS
    MpServer
    1.77
    reverse
    1.64
    WARD
    1.64
    terday
    1.60
    ALLY
    1.55
    rary
    1.55
    redd
    1.48
    ーク
    1.48
    VERT
    1.48
    VAL
    1.46
    Act Density 0.000%

    No Known Activations