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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating positive outcomes or promising results

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

    promising and encouraging results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.40
     agujas
    -0.36
    BufferException
    -0.36
     muñecas
    -0.35
    RTSC
    -0.34
     Primaria
    -0.34
    ValueStyle
    -0.34
     inglesa
    -0.34
     المعيارى
    -0.33
     cuddle
    -0.31
    POSITIVE LOGITS
     promising
    0.78
     prospects
    0.76
     hopeful
    0.69
     optimistic
    0.60
     Prospects
    0.59
     confident
    0.58
    spects
    0.58
     pessimism
    0.55
     expectations
    0.55
     promises
    0.53
    Act Density 0.173%

    No Known Activations