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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being under pressure or threat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     QUI
    -0.15
    bak
    -0.15
    chas
    -0.14
    :checked
    -0.14
    Ïĥο
    -0.14
    ucher
    -0.14
    -api
    -0.14
     conc
    -0.14
    shal
    -0.14
     Nez
    -0.14
    POSITIVE LOGITS
     suspicion
    0.17
     pressure
    0.16
     attack
    0.16
    ursor
    0.15
    647
    0.15
    TestClass
    0.15
    738
    0.15
    زار
    0.15
    ä¿ĿæĬ¤
    0.15
    hill
    0.14
    Act Density 0.025%

    No Known Activations