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

    Neuronpedia

    INDEX
    Explanations

    statements related to accusations or allegations in a political context

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    counting and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Imp
    -0.52
     Apar
    -0.51
     Clinic
    -0.51
     Kemp
    -0.51
    riae
    -0.49
    mano
    -0.49
    imensional
    -0.49
     Chal
    -0.48
    enderror
    -0.48
     Holt
    -0.47
    POSITIVE LOGITS
     zijne
    0.74
     mijne
    0.69
     avoient
    0.67
     Soyez
    0.66
     ainfi
    0.66
     Şi
    0.66
     asemenea
    0.66
     Monfieur
    0.66
     vocale
    0.64
     propOrder
    0.64
    Act Density 0.023%

    No Known Activations