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

    Neuronpedia

    INDEX
    Explanations

    declarations of various kinds, such as political declarations, emergency declarations, and personal declarations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to declarations or formal announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.76
    dding
    -0.73
    rouse
    -0.69
    zl
    -0.68
     sugg
    -0.68
     incent
    -0.66
     suggestion
    -0.65
     partName
    -0.64
     coax
    -0.64
     persu
    -0.63
    POSITIVE LOGITS
     innocence
    1.05
     independence
    0.95
     allegiance
    0.95
     neutrality
    0.90
     caliphate
    0.90
     unconstitutional
    0.89
    ocide
    0.88
     moratorium
    0.86
    independence
    0.86
     truce
    0.86
    Act Density 0.177%

    No Known Activations