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

    Neuronpedia

    INDEX
    Explanations

    references to vocabulary complexity and language use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portály
    -0.68
    ConstraintMaker
    -0.62
    AutoScale
    -0.62
    getCmp
    -0.61
    Hozzáférés
    -0.60
     DBNull
    -0.59
    Bakgrunnsstoff
    -0.57
     userSchema
    -0.56
    EFAULT
    -0.53
    Cubit
    -0.52
    POSITIVE LOGITS
     words
    0.95
     phrases
    0.88
     sentences
    0.84
     sentence
    0.83
     word
    0.82
     Words
    0.82
    Words
    0.81
     phrase
    0.76
    sentence
    0.70
     Phrase
    0.70
    Act Density 0.436%

    No Known Activations