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

    Neuronpedia

    INDEX
    Explanations

    phrases related to projects or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    statements that emphasize the significance or effectiveness of a model or strategy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aired
    -0.87
    .*
    -0.77
    %:
    -0.71
     Supports
    -0.70
    ãĢij
    -0.69
    itles
    -0.68
     Released
    -0.67
    â
    -0.66
    .(
    -0.65
     Ago
    -0.64
    POSITIVE LOGITS
     absolutely
    1.19
     unbelievable
    1.16
     tremendously
    1.14
     tremendous
    1.12
     definitely
    1.10
     phenomenal
    1.09
     unbelievably
    1.06
     really
    1.05
     extraordinarily
    1.05
     terrific
    1.02
    Act Density 0.412%

    No Known Activations