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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udd
    -0.15
    Confirmation
    -0.14
    è§
    -0.13
    æĮĻ
    -0.13
    íĥĿ
    -0.13
    çľ
    -0.13
    alice
    -0.13
     GLfloat
    -0.13
     safely
    -0.12
     widespread
    -0.12
    POSITIVE LOGITS
     discipline
    0.35
     discipl
    0.34
     disciplinary
    0.32
     correction
    0.31
     span
    0.31
     reb
    0.31
     lect
    0.30
     stern
    0.30
     spanking
    0.30
     disciplines
    0.28
    Act Density 0.549%

    No Known Activations