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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of making something better or more meaningful

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "it" to describe actions or states

    np_acts-logits-general · gemini-2.0-flash

    make it appear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secours
    -0.66
     pleaſure
    -0.65
     myſelf
    -0.60
     poffe
    -0.57
    Према
    -0.56
     polaire
    -0.56
     alſo
    -0.56
     againſt
    -0.56
    الإنجليزية
    -0.56
     themſelves
    -0.55
    POSITIVE LOGITS
     happen
    0.88
     appear
    0.87
     seem
    0.86
     look
    0.86
     easier
    0.79
     feel
    0.79
     available
    0.77
     accessible
    0.75
     possible
    0.73
     aware
    0.69
    Act Density 0.138%

    No Known Activations