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

    Neuronpedia

    INDEX
    Explanations

    references to popular films and their critical reception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imidlertid
    -0.53
    GenerationType
    -0.53
    mbic
    -0.52
    ditor
    -0.51
     démission
    -0.50
    dimento
    -0.49
    vastava
    -0.49
    Skocz
    -0.48
    ectoria
    -0.47
    catore
    -0.46
    POSITIVE LOGITS
     Transformers
    0.68
     Harry
    0.63
     Hobbit
    0.61
     المعيارى
    0.60
    transformers
    0.59
     Pokémon
    0.59
     franchise
    0.58
     transformers
    0.57
     franchises
    0.57
    adaptiveStyles
    0.57
    Act Density 0.229%

    No Known Activations