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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating experiences or processes involving challenges or struggles

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

    passage through experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disponibilités
    -0.53
     gynhyrchwyd
    -0.51
    bbene
    -0.50
     Exactos
    -0.50
     оригіналу
    -0.49
    styleType
    -0.47
    الحياه
    -0.46
    ochlor
    -0.44
    abestanden
    -0.44
    amını
    -0.43
    POSITIVE LOGITS
     undergo
    0.53
    experienced
    0.47
     undergoes
    0.47
     underwent
    0.46
     undergone
    0.45
    Experienced
    0.45
     undergoing
    0.43
     experienced
    0.43
     procédures
    0.42
    inSlope
    0.40
    Act Density 0.011%

    No Known Activations