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

    Neuronpedia

    INDEX
    Explanations

    words related to building and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.20
    eration
    -0.17
    sar
    -0.16
    ered
    -0.16
    oring
    -0.15
    ORED
    -0.15
    eries
    -0.15
    rooms
    -0.14
    le
    -0.14
    aman
    -0.14
    POSITIVE LOGITS
     Blocks
    0.23
     blocks
    0.22
    SMART
    0.22
     codes
    0.20
     envelope
    0.20
     materials
    0.20
     Materials
    0.19
    Blocks
    0.19
     Codes
    0.19
     code
    0.19
    Act Density 0.016%

    No Known Activations