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

    Neuronpedia

    INDEX
    Explanations

    references to medical symptoms and self-referential phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.99
    
    -0.85
    posedge
    -0.84
     itſelf
    -0.78
     weren
    -0.74
     Majefty
    -0.72
     $_"
    -0.69
     tienden
    -0.69
    addPreferredGap
    -0.69
    PositiveButton
    -0.68
    POSITIVE LOGITS
     am
    0.69
     sono
    0.65
     Gre
    0.64
     facing
    0.64
     deployed
    0.60
    ımda
    0.54
    Sono
    0.54
     suis
    0.53
     I
    0.53
     im
    0.52
    Act Density 0.234%

    No Known Activations