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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating someone taking control or responsibility

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

    took over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SetBool
    -0.47
    Erstellt
    -0.41
     EdgeInsets
    -0.41
     MenuView
    -0.39
    httphttps
    -0.38
    Dichloropropane
    -0.36
     án
    -0.36
    xase
    -0.36
     p
    -0.35
     Marsh
    -0.35
    POSITIVE LOGITS
    ſelf
    0.66
     responsibility
    0.63
     provisoire
    0.63
    awtextra
    0.63
    ſelves
    0.59
     temporaire
    0.57
     übernehmen
    0.53
     avoient
    0.53
    ownership
    0.53
     poffe
    0.53
    Act Density 0.012%

    No Known Activations