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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate planning or actions to be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inclusive
    -0.17
    ãĥ¼ãĥģ
    -0.16
    енÑĤÑĥ
    -0.15
    ãĥ¼ãĤ¸
    -0.15
     continu
    -0.15
    ä¹ħä¹ħ
    -0.15
    leftright
    -0.15
    stay
    -0.14
    ersist
    -0.14
    inclusive
    -0.14
    POSITIVE LOGITS
    ereg
    0.18
     introduced
    0.15
     Sing
    0.15
     seriously
    0.15
     reg
    0.14
     serious
    0.14
     Parr
    0.14
     stop
    0.14
     pity
    0.14
     interfering
    0.14
    Act Density 0.047%

    No Known Activations