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

    Neuronpedia

    INDEX
    Explanations

    invitations and welcoming phrases

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

    invite and set forth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.58
     Савезне
    -0.48
     дописавши
    -0.44
     Gegenteil
    -0.43
     Мексичка
    -0.42
    contentLoaded
    -0.40
    íně
    -0.40
    rawDesc
    -0.39
    boru
    -0.39
     담
    -0.39
    POSITIVE LOGITS
     invite
    0.51
    Hozzáférés
    0.48
     Invite
    0.46
    +#+
    0.45
    ResponseWriter
    0.45
    saraba
    0.44
     Signalez
    0.42
    Visitors
    0.42
     Visitors
    0.41
     Friends
    0.40
    Act Density 0.001%

    No Known Activations