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

    Neuronpedia

    INDEX
    Explanations

    phrases related to bricks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "brick"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.82
    ntil
    -0.81
     Voters
    -0.76
    uters
    -0.71
    ittee
    -0.67
     NOTICE
    -0.67
     Elections
    -0.65
    etheus
    -0.65
    opausal
    -0.64
     Hearing
    -0.62
    POSITIVE LOGITS
     brick
    1.23
     bricks
    1.19
    bats
    1.19
    layer
    1.10
     Brick
    1.01
    MpServer
    0.95
    shaw
    0.91
    mort
    0.86
     mortar
    0.85
    jee
    0.81
    Act Density 0.006%

    No Known Activations