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

    Neuronpedia

    INDEX
    Explanations

    discussions related to honesty and vulnerability in difficult situations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.84
     cherchés
    -0.72
    tagHelperRunner
    -0.70
    enumi
    -0.69
    Спољашње
    -0.68
    saraba
    -0.66
    存于互联网档案馆
    -0.65
    !("{
    -0.65
     BrowserModule
    -0.65
    だったが
    -0.62
    POSITIVE LOGITS
     yourself
    1.65
    yourself
    1.31
     Yourself
    1.21
     YOURSELF
    1.20
     your
    1.20
    your
    1.14
     yourselves
    1.13
    Yourself
    1.05
    Your
    1.04
     Your
    0.96
    Act Density 0.454%

    No Known Activations