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

    Neuronpedia

    INDEX
    Explanations

    terms related to sanctions and embargoes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tolerate
    -0.15
    éľ²
    -0.15
    laus
    -0.14
    046
    -0.14
    ÙĥÙĬÙĦ
    -0.14
    pered
    -0.13
    filt
    -0.13
    642
    -0.13
     runaway
    -0.13
    ãĥ¥
    -0.13
    POSITIVE LOGITS
     sanctions
    0.41
     embargo
    0.27
     sanction
    0.27
     penalties
    0.25
    san
    0.23
     freezes
    0.21
     pressure
    0.20
     imposed
    0.20
     penalty
    0.20
     freezing
    0.20
    Act Density 0.073%

    No Known Activations