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

    Neuronpedia

    INDEX
    Explanations

    references to community support and collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adem
    -0.17
    ãĤ¤ãĥ¤
    -0.17
    erras
    -0.14
    .setColumns
    -0.14
    ziej
    -0.14
     bergen
    -0.13
    享
    -0.13
    alsa
    -0.13
    quet
    -0.13
    ivor
    -0.13
    POSITIVE LOGITS
     step
    0.35
     stepped
    0.34
     jump
    0.33
     jumped
    0.32
     jumps
    0.31
    jump
    0.30
     Jump
    0.29
     jumping
    0.29
     chim
    0.28
     steps
    0.28
    Act Density 0.640%

    No Known Activations