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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions in a specific context or scenario

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.68
    nil
    -0.62
    $.
    -0.56
    edin
    -0.56
    Introduced
    -0.54
    Math
    -0.53
    Fle
    -0.53
    grand
    -0.52
    fleet
    -0.52
    æ³
    -0.51
    POSITIVE LOGITS
    gery
    0.98
    cing
    0.93
    geries
    0.92
    bidden
    0.92
     instance
    0.88
     example
    0.87
    aging
    0.79
    gotten
    0.74
    ced
    0.74
    WARD
    0.73
    Act Density 0.276%

    No Known Activations