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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.73
    ccording
    -0.68
     diver
    -0.64
     contradicted
    -0.64
    */(
    -0.60
     lured
    -0.60
    å°Ĩ
    -0.59
    ULTS
    -0.59
     refuted
    -0.59
     displ
    -0.57
    POSITIVE LOGITS
     goodness
    1.27
     heavens
    1.16
    fulness
    1.14
    giving
    1.09
     god
    1.05
     God
    1.01
    ful
    0.99
    god
    0.96
    fully
    0.95
    SG
    0.94
    Act Density 0.029%

    No Known Activations