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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.67
    ople
    -0.63
    rolet
    -0.62
    Gear
    -0.62
    rous
    -0.61
    scene
    -0.57
    rent
    -0.57
    oller
    -0.56
    rol
    -0.56
    OUS
    -0.55
    POSITIVE LOGITS
    pired
    1.09
     well
    1.00
    bestos
    0.98
     opposed
    0.97
    pires
    0.96
    ynchron
    0.88
     evidenced
    0.87
    criptions
    0.86
    phy
    0.85
     regards
    0.83
    Act Density 0.262%

    No Known Activations