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

    Neuronpedia

    INDEX
    Explanations

    specific numerical phrases and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     libremente
    -0.46
     Bewußt
    -0.45
    SequentialGroup
    -0.45
     Ensino
    -0.44
     cerámica
    -0.39
     chiara
    -0.39
     DbSet
    -0.39
    AutoField
    -0.38
     Penga
    -0.37
     bahía
    -0.37
    POSITIVE LOGITS
    msgTypes
    0.61
    msgSender
    0.57
     nakalista
    0.56
    pushFollow
    0.54
    FDP
    0.53
    ècie
    0.53
     Mile
    0.52
    metheus
    0.51
     getRule
    0.51
    REASONS
    0.51
    Act Density 0.486%

    No Known Activations