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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components, specifically checkboxes and their states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    l
    -0.65
    i
    -0.63
    I
    -0.55
    uc
    -0.54
    r
    -0.53
    kom
    -0.53
    ...
    -0.53
     be
    -0.52
    h
    -0.52
    u
    -0.52
    POSITIVE LOGITS
    Checked
    2.37
    checked
    2.37
     Checked
    2.26
     checked
    2.15
     Checking
    1.76
     checking
    1.66
    Checking
    1.59
    CHECKED
    1.58
    checking
    1.48
     isChecked
    1.31
    Act Density 0.140%

    No Known Activations