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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.03
    2:0.14
    3:0.07
    4:0.14
    5:0.05
    6:0.05
    7:0.03
    8:0.06
    9:0.08
    10:0.08
    11:0.05
    Negative Logits
     wors
    -1.51
     ONLY
    -1.45
     except
    -1.44
     owing
    -1.40
     inheritance
    -1.39
    direction
    -1.37
     WHERE
    -1.37
    ")
    -1.36
    "),
    -1.35
     imports
    -1.35
    POSITIVE LOGITS
    senal
    1.85
     Burton
    1.81
     Neal
    1.80
    田
    1.79
    verett
    1.79
    HAEL
    1.73
    letcher
    1.68
     Monte
    1.65
    ijah
    1.65
     Leslie
    1.64
    Act Density 0.067%

    No Known Activations