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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms that indicate variability and dependency between factors in data or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    degree of dependence or variation

    np_acts-logits-general · gemini-2.0-flash

    intensity and dependence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.59
    Personendaten
    -0.53
    orithmic
    -0.50
    MethodManager
    -0.48
    الحياه
    -0.47
    hilation
    -0.47
     ligiloj
    -0.46
    InputTagHelper
    -0.45
    乓
    -0.45
    Diwedd
    -0.44
    POSITIVE LOGITS
     heavily
    0.65
     fuertemente
    0.63
     fortemente
    0.59
     strongly
    0.58
     מאוד
    0.56
     Highly
    0.56
     highly
    0.54
     greatly
    0.53
     Many
    0.53
     Strongly
    0.52
    Act Density 1.282%

    No Known Activations