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

    Neuronpedia

    INDEX
    Explanations

    instances of intimate and potentially non-consensual interactions

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

    Following prepositions and locations

    np_acts-logits-general · gemini-2.0-flash

    social locations and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TokenNameDOT
    -0.43
     reported
    -0.36
     Davidson
    -0.35
    DebuggerNonUser
    -0.35
    igel
    -0.34
    holtz
    -0.34
    hlen
    -0.34
     Matta
    -0.34
     larger
    -0.33
     nahilalakip
    -0.33
    POSITIVE LOGITS
    yntaxException
    0.67
     Мексичка
    0.50
     Meksiku
    0.49
    ſelves
    0.47
    oprecipitation
    0.47
     zove
    0.46
     дописавши
    0.45
    BagLayout
    0.45
    AndroidJUnit
    0.44
    anthene
    0.43
    Act Density 0.283%

    No Known Activations