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

    Neuronpedia

    INDEX
    Explanations

    concepts related to personal beliefs and religious affiliation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.73
    UrlResolution
    -0.59
     <<<<<<<<<<<<<<
    -0.59
    jooq
    -0.57
    writeFieldEnd
    -0.52
    awtextra
    -0.50
    RegressionTest
    -0.50
    HasBeenSet
    -0.47
    GeneratedCode
    -0.47
    kk
    -0.46
    POSITIVE LOGITS
     myself
    0.92
     ourselves
    0.87
     Yourself
    0.81
     yourself
    0.74
    myself
    0.73
     Myself
    0.68
     YOURSELF
    0.68
     herself
    0.67
    yourself
    0.67
     himself
    0.64
    Act Density 0.321%

    No Known Activations