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

    Neuronpedia

    INDEX
    Explanations

    emotions and states of awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.17
    Ỽ
    -0.16
    alion
    -0.15
    halt
    -0.15
    ROP
    -0.15
    AFX
    -0.15
    веÑĢ
    -0.15
     ngược
    -0.15
    ãĥ¼ãĥ«
    -0.14
    .Restr
    -0.14
    POSITIVE LOGITS
     upon
    0.18
     Upon
    0.16
    à¤Ĺल
    0.15
    .sap
    0.15
    ="__
    0.15
     Walton
    0.15
    Upon
    0.15
     Kling
    0.14
    ux
    0.14
    iffer
    0.13
    Act Density 0.097%

    No Known Activations