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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve invitations or suggestions for participation

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

    coming and going

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bloss
    -0.50
     polaire
    -0.49
     Bolo
    -0.48
    DDR
    -0.47
    Portály
    -0.47
    issauga
    -0.46
    DDG
    -0.46
    roja
    -0.46
     resourceCulture
    -0.45
    luiting
    -0.45
    POSITIVE LOGITS
     CanadaChoose
    0.49
    InputBorder
    0.45
    Personensuche
    0.44
    SceneManagement
    0.42
    writerow
    0.42
     resultCode
    0.41
     argc
    0.41
    +:+
    0.40
     Signalez
    0.40
     venido
    0.39
    Act Density 0.005%

    No Known Activations