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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "different" and its variations indicating contrast or distinction

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

    following "different" or "similar"

    np_acts-logits-general · gemini-2.0-flash

    comparing different things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nutie
    -0.49
    værende
    -0.48
     extra
    -0.48
    veless
    -0.46
     certain
    -0.46
    ález
    -0.45
    สือ
    -0.45
    UpInside
    -0.44
     trasferimento
    -0.44
    ண்டு
    -0.43
    POSITIVE LOGITS
     kinds
    0.84
    IATION
    0.84
     than
    0.80
     coloured
    0.79
     sized
    0.79
     approaches
    0.78
     colored
    0.75
     AssemblyCulture
    0.73
     niż
    0.72
     Approaches
    0.72
    Act Density 0.249%

    No Known Activations