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

    Neuronpedia

    INDEX
    Explanations

    references to buildings and building-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sar
    -0.22
    cha
    -0.17
    ios
    -0.16
    ivate
    -0.16
    ableView
    -0.16
    sheets
    -0.15
    eer
    -0.15
    ãĥĨãĥ«
    -0.15
    rig
    -0.15
    erek
    -0.15
    POSITIVE LOGITS
     Blocks
    0.23
     blocks
    0.22
    -block
    0.21
    SMART
    0.21
    blocks
    0.20
    Blocks
    0.20
     envelope
    0.19
     block
    0.18
    alist
    0.17
    block
    0.17
    Act Density 0.029%

    No Known Activations