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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating planning or future intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SerializedName
    -0.58
    BeginContext
    -0.55
     Crim
    -0.53
    polation
    -0.51
     recent
    -0.51
    Zitat
    -0.51
    recent
    -0.49
    __(/*!
    -0.48
     समीक्षक
    -0.48
    nictwa
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.73
     definitive
    0.56
     définiti
    0.55
     definitivo
    0.54
     défin
    0.54
     لينك
    0.51
     konkrét
    0.51
    RegistryLite
    0.51
    Decide
    0.50
    entuan
    0.50
    Act Density 0.458%

    No Known Activations