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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal beliefs and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to social interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.64
    å°Ĩ
    -0.54
    ±
    -0.53
    ãĥŃ
    -0.52
    wcsstore
    -0.52
    æ©Ł
    -0.52
    ãĥĥãĥĪ
    -0.51
    axter
    -0.47
     Bundes
    -0.47
    NSA
    -0.46
    POSITIVE LOGITS
     whilst
    0.84
     because
    0.75
    .",
    0.69
     whereas
    0.68
    ;
    0.64
     whenever
    0.64
     ('
    0.62
    .;
    0.59
    .","
    0.59
     while
    0.59
    Act Density 1.776%

    No Known Activations