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

    Neuronpedia

    INDEX
    Explanations

    names or titles with military or police ranks

    oai_token-act-pair · gpt-3.5-turbo

    military titles and related abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.83
    DragonMagazine
    -0.68
     doub
    -0.55
    initialized
    -0.51
     outcry
    -0.51
     heck
    -0.51
    WIND
    -0.51
    handed
    -0.51
    iHUD
    -0.50
    LOCK
    -0.50
    POSITIVE LOGITS
    .,
    1.54
    ./
    1.48
    .:
    1.47
    .;
    1.37
    .?
    1.30
    .-
    1.28
    .),
    1.23
    .):
    1.23
    .).
    1.19
    .—
    1.09
    Act Density 0.104%

    No Known Activations