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

    Neuronpedia

    INDEX
    Explanations

    descriptions of artistic design and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.82
    ſelf
    -0.75
    లాలు
    -0.71
    rhosis
    -0.71
     myſelf
    -0.69
     embarrassing
    -0.69
    ſelves
    -0.69
     iſt
    -0.69
     Selama
    -0.69
     houſe
    -0.69
    POSITIVE LOGITS
     subtle
    0.84
     contrast
    0.78
     contrasting
    0.72
     contrasts
    0.71
     kont
    0.67
     subtly
    0.67
     bold
    0.66
     контра
    0.65
     kontra
    0.62
     harmonious
    0.61
    Act Density 0.223%

    No Known Activations