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

    Neuronpedia

    INDEX
    Explanations

    words related to food and culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somewhat
    -0.86
    somewhat
    -0.82
     occasionally
    -0.82
     sometimes
    -0.74
     occasional
    -0.71
     slightly
    -0.69
     agak
    -0.68
    sometimes
    -0.66
     geleg
    -0.66
     perhaps
    -0.65
    POSITIVE LOGITS
     unbelievably
    1.22
     incredible
    1.18
     unbelievable
    1.14
     unglaub
    1.07
    incredible
    1.06
     incredibly
    1.05
     incroyable
    1.02
     absolutely
    1.02
    Incredible
    0.98
    AMAZING
    0.98
    Act Density 0.254%

    No Known Activations