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

    Neuronpedia

    INDEX
    Explanations

    phrases or punctuation that indicate changes in state or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.66
    addCriterion
    -0.54
    μαστε
    -0.53
    hod
    -0.51
    endphp
    -0.50
     vPvB
    -0.49
    ìm
    -0.48
    __":
    -0.48
     (+
    -0.48
    yes
    -0.47
    POSITIVE LOGITS
     although
    0.94
     thus
    0.83
     whereas
    0.78
     thereby
    0.76
     leading
    0.70
    HtmlAttribute
    0.67
     liknande
    0.67
     while
    0.66
     similarly
    0.65
     furthermore
    0.64
    Act Density 0.929%

    No Known Activations