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

    Neuronpedia

    INDEX
    Explanations

    terms related to acquisition or obtaining something

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

    Gottlieb et al. predicated on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VYMaps
    -0.62
     ſche
    -0.55
    Geplaatst
    -0.54
     impeach
    -0.53
    ांकि
    -0.52
    colat
    -0.52
    ectady
    -0.52
    ölkerung
    -0.52
     صوتيه
    -0.51
     Auditing
    -0.50
    POSITIVE LOGITS
    得
    2.23
     得
    1.75
    得不
    1.02
    也得
    0.88
    就得
    0.83
    得好
    0.79
    得上
    0.78
    得多
    0.72
    得太
    0.72
    得了
    0.71
    Act Density 0.001%

    No Known Activations