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

    Neuronpedia

    INDEX
    Explanations

    parentheses and markers that denote sections or lists in scientific or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irical
    -0.60
    daille
    -0.58
    prem
    -0.57
     piezo
    -0.56
     SWT
    -0.56
    horabuena
    -0.55
     MainAxisSize
    -0.54
     Abstraction
    -0.54
    valbard
    -0.54
     einger
    -0.52
    POSITIVE LOGITS
    -,
    1.08
    -.
    0.99
    -)
    0.95
    -(
    0.93
    --.
    0.87
    ("");
    0.86
    -;
    0.84
    -->
    0.83
    -"
    0.80
    -'
    0.76
    Act Density 0.115%

    No Known Activations