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

    Neuronpedia

    INDEX
    Explanations

    future-oriented verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.10
    3:0.07
    4:0.09
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
     revolt
    -2.12
     Mean
    -2.11
     mockery
    -2.04
     1936
    -1.98
     Scha
    -1.93
     Sons
    -1.90
     Herm
    -1.87
     doomed
    -1.87
     spitting
    -1.83
     1896
    -1.82
    POSITIVE LOGITS
    ら
    2.43
    taboola
    2.30
    microsoft
    2.20
    さ
    2.18
    き
    2.16
    wayne
    2.13
    eric
    2.09
    INESS
    2.09
    76561
    2.05
    oxin
    2.03
    Act Density 0.000%

    No Known Activations