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

    Neuronpedia

    INDEX
    Explanations

    occurrences of social and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.13
    3:0.26
    4:0.14
    5:0.02
    6:0.02
    7:0.05
    8:0.05
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
    assic
    -1.52
     accounted
    -1.52
    "?
    -1.43
     guiActiveUn
    -1.43
     outwe
    -1.39
    "}
    -1.32
    lance
    -1.31
    artney
    -1.30
    …"
    -1.30
    "},
    -1.29
    POSITIVE LOGITS
     illustrating
    1.30
     discusses
    1.29
    :]
    1.28
     illustrates
    1.28
    leans
    1.25
     dich
    1.24
     succinct
    1.24
     explores
    1.23
     revealing
    1.23
     reader
    1.23
    Act Density 0.612%

    No Known Activations