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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence and cognitive abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.80
     pleaſure
    -0.77
     themſelves
    -0.76
     himſelf
    -0.76
     itſelf
    -0.74
     Reſ
    -0.73
     ſeveral
    -0.73
    ftagPool
    -0.70
     leſs
    -0.70
     ſmall
    -0.67
    POSITIVE LOGITS
     intelligence
    0.89
     INTEL
    0.84
     intellectual
    0.81
     intelligent
    0.81
     Intel
    0.72
    Intel
    0.71
    Gut
    0.69
     intellect
    0.68
    Track
    0.68
     gut
    0.68
    Act Density 0.084%

    No Known Activations