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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "say" or its variations indicating statements or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folios
    -0.74
    thia
    -0.70
    ghazi
    -0.68
    theless
    -0.67
    aughs
    -0.67
    infeld
    -0.66
    estern
    -0.63
    phant
    -0.62
    ocobo
    -0.61
    anz
    -0.60
    POSITIVE LOGITS
     goodbye
    1.10
    oras
    0.72
    ysis
    0.71
     Goodbye
    0.66
    ially
    0.64
     colours
    0.63
     farewell
    0.63
    ogun
    0.62
    ieu
    0.61
     bye
    0.61
    Act Density 0.120%

    No Known Activations