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

    Neuronpedia

    INDEX
    Explanations

    references to events or activities involving communal gatherings and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.04
    2:0.05
    3:0.05
    4:0.09
    5:0.04
    6:0.05
    7:0.05
    8:0.05
    9:0.05
    10:0.04
    11:0.37
    Negative Logits
     ­
    -3.16
    ewitness
    -2.76
    ‑
    -2.73
    ­
    -2.64
     casinos
    -2.57
    perty
    -2.56
    CLOSE
    -2.54
     rive
    -2.51
     Aires
    -2.48
     oun
    -2.38
    POSITIVE LOGITS
     /
    5.99
    /
    4.77
    /-
    4.41
    /?
    4.33
    /_
    4.18
    /(
    4.18
    ./
    4.17
    /.
    4.14
    /,
    4.09
    =/
    4.05
    Act Density 0.005%

    No Known Activations