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

    Neuronpedia

    INDEX
    Explanations

    terms related to moral judgment and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spiritual or moral value judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     layers
    -0.39
     hus
    -0.39
     kernels
    -0.38
     secretive
    -0.38
     Reef
    -0.37
     Cheong
    -0.37
    ãĢIJ
    -0.36
    enei
    -0.36
     �
    -0.36
     fer
    -0.36
    POSITIVE LOGITS
    tenance
    0.71
    assador
    0.60
    iversary
    0.57
    ãĤ¨ãĥ«
    0.56
    ardless
    0.55
    soDeliveryDate
    0.51
    jamin
    0.50
    iamond
    0.49
    terday
    0.49
    igenous
    0.48
    Act Density 1.534%

    No Known Activations