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

    Neuronpedia

    INDEX
    Explanations

    various mathematical symbols and notation associated with equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ={({
    -0.75
     ====
    -0.65
    𝓲
    -0.62
    illon
    -0.61
     IDA
    -0.61
     ros
    -0.60
    σιμοποι
    -0.59
    çı
    -0.59
     σύν
    -0.58
    Callbacks
    -0.56
    POSITIVE LOGITS
     ^
    2.08
    .^
    1.87
    ("^
    1.82
    '^
    1.81
     "^
    1.80
     '^
    1.79
    ^^^
    1.76
    :^
    1.64
    -^
    1.63
    "^
    1.59
    Act Density 0.297%

    No Known Activations