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

    Neuronpedia

    INDEX
    Explanations

    instances of output-related commands and functions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -0.98
     zijne
    -0.87
     iſt
    -0.86
     itſelf
    -0.84
     desmotivaciones
    -0.83
     indígen
    -0.83
     betweenstory
    -0.83
     Мексичка
    -0.82
     imagui
    -0.79
     myſelf
    -0.79
    POSITIVE LOGITS
     amongst
    0.59
     among
    0.58
     Harbour
    0.58
     much
    0.53
     harbour
    0.50
     Among
    0.48
    among
    0.48
     Amongst
    0.47
    ough
    0.46
     parked
    0.46
    Act Density 0.412%

    No Known Activations