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

    Neuronpedia

    INDEX
    Explanations

    words related to theft or deception

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "seals" or certification, particularly in a legal or corporate context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sul
    -0.69
    fact
    -0.67
     Poc
    -0.64
     Newsp
    -0.63
     table
    -0.63
     Benz
    -0.62
     Vu
    -0.60
     Barkley
    -0.60
     Places
    -0.59
     Gael
    -0.59
    POSITIVE LOGITS
    eal
    1.05
    ously
    0.87
    ier
    0.83
    ily
    0.82
    estine
    0.82
    efully
    0.80
    ater
    0.79
    owship
    0.79
    enge
    0.78
    istic
    0.77
    Act Density 0.008%

    No Known Activations