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

    Neuronpedia

    INDEX
    Explanations

    directional phrases and positional references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.03
    2:0.12
    3:0.04
    4:0.07
    5:0.03
    6:0.08
    7:0.05
    8:0.14
    9:0.03
    10:0.09
    11:0.19
    Negative Logits
    icago
    -1.49
    ById
    -1.39
     Divide
    -1.39
    DonaldTrump
    -1.38
     unity
    -1.35
    nels
    -1.32
    ftime
    -1.31
    Balance
    -1.31
    ICO
    -1.31
    Baltimore
    -1.31
    POSITIVE LOGITS
    unal
    1.41
     sympathetic
    1.29
    rehend
    1.28
     charism
    1.26
    voice
    1.25
     interviewed
    1.24
     stimulating
    1.20
     extrater
    1.19
     Luxem
    1.19
     actors
    1.18
    Act Density 0.001%

    No Known Activations