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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting marks that indicate structure or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ControllerAdvice
    -0.52
    Rptr
    -0.52
    جمعیت
    -0.50
    Citiți
    -0.50
     numerus
    -0.48
    стта
    -0.46
     тут
    -0.46
    icznego
    -0.45
    sense
    -0.45
    ibi
    -0.44
    POSITIVE LOGITS
     something
    0.97
     according
    0.83
     although
    0.81
    something
    0.80
     prompting
    0.78
     marking
    0.70
     joining
    0.69
     effectively
    0.68
     though
    0.68
     sparking
    0.67
    Act Density 0.284%

    No Known Activations