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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical holes

    oai_token-act-pair · gpt-3.5-turbo

    references to holes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cia
    -0.82
    ullivan
    -0.72
     livest
    -0.69
    NetMessage
    -0.69
    against
    -0.68
    Bal
    -0.65
    ione
    -0.65
    anche
    -0.64
    ggles
    -0.64
     Garner
    -0.63
    POSITIVE LOGITS
     hole
    1.27
     holes
    1.22
     drilled
    1.16
    hole
    1.15
     Hole
    1.10
     dug
    1.02
    holes
    0.97
     punched
    0.89
    pots
    0.85
     poked
    0.84
    Act Density 0.049%

    No Known Activations