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

    Neuronpedia

    INDEX
    Explanations

    mentions of panels and their functions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pip
    -0.19
    orks
    -0.16
     Pierce
    -0.16
     Pink
    -0.15
    ycz
    -0.15
    icorn
    -0.15
     cones
    -0.14
    Plug
    -0.13
     Pipe
    -0.13
     Poz
    -0.13
    POSITIVE LOGITS
     pan
    0.87
     panel
    0.78
    Pan
    0.73
    panel
    0.69
     Pan
    0.68
     Panel
    0.68
    _pan
    0.68
    pan
    0.67
     panels
    0.67
    -panel
    0.66
    Act Density 0.091%

    No Known Activations