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

    Neuronpedia

    INDEX
    Explanations

    expressions that convey a sense of approximation or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a degree of similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osa
    -0.77
     Sands
    -0.75
    afety
    -0.69
     Mitchell
    -0.69
     Burgess
    -0.68
    lin
    -0.67
     Canterbury
    -0.67
    jl
    -0.67
     Lov
    -0.64
    byn
    -0.64
    POSITIVE LOGITS
    etheless
    0.84
     mileage
    0.74
     indistinguishable
    0.69
     retard
    0.68
     identical
    0.68
     equivalent
    0.68
    ingu
    0.67
     cosmetic
    0.67
     unint
    0.64
     intact
    0.64
    Act Density 0.021%

    No Known Activations