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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making official statements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declare" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.74
    umbn
    -0.70
    RH
    -0.67
    dayName
    -0.67
    nesota
    -0.66
    atana
    -0.65
    ramid
    -0.65
    «ĺ
    -0.64
    Pg
    -0.64
    alez
    -0.64
    POSITIVE LOGITS
     allegiance
    0.90
     bankruptcy
    0.88
    phas
    0.82
    ignty
    0.80
     martial
    0.76
    aration
    0.75
     declares
    0.75
     declared
    0.74
    ance
    0.74
     unequivocally
    0.74
    Act Density 0.031%

    No Known Activations