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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal and professional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.25
    1:0.04
    2:0.01
    3:0.12
    4:0.07
    5:0.07
    6:0.04
    7:0.02
    8:0.24
    9:0.05
    10:0.01
    11:0.03
    Negative Logits
    enium
    -1.78
     uniformly
    -1.64
     nort
    -1.57
     blinked
    -1.54
     orange
    -1.52
     cloudy
    -1.51
    ammers
    -1.51
     clustered
    -1.51
     stabilized
    -1.50
    terday
    -1.49
    POSITIVE LOGITS
     memoir
    1.80
    personal
    1.76
     intimate
    1.74
    ebin
    1.71
     affairs
    1.69
     condol
    1.68
     autobiography
    1.64
    aryn
    1.61
     alias
    1.60
    Footnote
    1.59
    Act Density 0.042%

    No Known Activations