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

    Neuronpedia

    INDEX
    Explanations

    phrases related to greetings and welcoming messages

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

    come to this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.59
     Infórmanos
    -0.52
    -0.45
    reordered
    -0.45
    Jeografia
    -0.45
     ویکی‌پدی
    -0.45
    tagext
    -0.44
     autorytatywna
    -0.44
    TokenNameDOT
    -0.43
     nakalista
    -0.43
    POSITIVE LOGITS
     listeners
    0.48
     podcast
    0.47
     spectator
    0.46
    хьтан
    0.45
     guest
    0.45
     interviewer
    0.44
     interview
    0.43
     Audience
    0.43
    AutoScale
    0.43
     listener
    0.43
    Act Density 0.058%

    No Known Activations