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

    Neuronpedia

    INDEX
    Explanations

    terms related to building and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.21
    eration
    -0.18
    ORED
    -0.17
    erland
    -0.16
    oring
    -0.15
    ed
    -0.15
    deg
    -0.15
    sar
    -0.15
    over
    -0.15
    eries
    -0.15
    POSITIVE LOGITS
     Blocks
    0.25
     blocks
    0.25
    -block
    0.21
    Blocks
    0.21
    blocks
    0.21
     materials
    0.20
     BLOCK
    0.19
    _blocks
    0.19
     block
    0.19
     Materials
    0.18
    Act Density 0.019%

    No Known Activations