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

    Neuronpedia

    INDEX
    Explanations

    expressions related to planning and activities involving enjoyment and socialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StandardItem
    -0.16
    ContentLoaded
    -0.14
    roach
    -0.14
     ÑĥÑħод
    -0.14
    ãĥ³ãĥĩãĤ£
    -0.14
    ouch
    -0.13
    озем
    -0.13
     fart
    -0.13
    chg
    -0.13
    644
    -0.13
    POSITIVE LOGITS
     dish
    0.25
     rock
    0.24
    dish
    0.24
     score
    0.24
     party
    0.21
     stock
    0.21
     channel
    0.20
     saddle
    0.20
     deck
    0.20
     Score
    0.20
    Act Density 0.369%

    No Known Activations