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

    Neuronpedia

    INDEX
    Explanations

    language patterns involving comparisons and contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antaranya
    -0.73
     antaranya
    -0.70
     décennies
    -0.66
     générations
    -0.66
     rangs
    -0.65
     vermelhas
    -0.65
    fromCharCode
    -0.64
     épaules
    -0.63
     fathoms
    -0.61
     muun
    -0.61
    POSITIVE LOGITS
     humans
    0.73
     ddelweddau
    0.72
    こういう
    0.72
    这类
    0.69
     modern
    0.66
     подоб
    0.65
     solche
    0.65
    oneofs
    0.62
    InitVars
    0.62
    бычно
    0.62
    Act Density 0.843%

    No Known Activations