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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "dove" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Columbian doves and dovecot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OkHttpClient
    -0.64
    ruptcy
    -0.53
     Griechen
    -0.53
    yorsunuz
    -0.52
     Juifs
    -0.52
     băr
    -0.50
    rekli
    -0.49
    rsiniz
    -0.48
    iſen
    -0.47
     Histórico
    -0.46
    POSITIVE LOGITS
     Dove
    2.22
    Dove
    2.19
     dove
    2.19
    dove
    1.92
     doves
    1.41
     dov
    0.84
    OVE
    0.74
     paloma
    0.71
     Dov
    0.68
    dov
    0.65
    Act Density 0.001%

    No Known Activations