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

    Neuronpedia

    INDEX
    Explanations

    phrases related to persuasion and influence

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

    influence and its effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.59
    Geplaatst
    -0.55
    archiviato
    -0.49
     Económica
    -0.48
    Rujuakan
    -0.47
     AssemblyCompany
    -0.45
    windowFixed
    -0.45
    EnableWeb
    -0.45
     transfieras
    -0.45
    complexContent
    -0.44
    POSITIVE LOGITS
    influence
    0.62
     influence
    0.62
    影響
    0.59
     Influence
    0.56
    influ
    0.56
     influencing
    0.56
    Influ
    0.54
    Influence
    0.53
     invloed
    0.52
     впли
    0.50
    Act Density 0.090%

    No Known Activations