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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases related to identity and personal attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.03
     ſy
    -0.99
     BorderRadius
    -0.97
     itſelf
    -0.96
     themſelves
    -0.95
     Monfieur
    -0.94
     Diſ
    -0.93
     Reſ
    -0.92
    ########.
    -0.91
     Eſ
    -0.91
    POSITIVE LOGITS
     He
    0.64
     U
    0.61
     he
    0.60
     be
    0.60
     all
    0.57
    ...
    0.56
     not
    0.55
     I
    0.54
     it
    0.54
     Be
    0.53
    Act Density 0.529%

    No Known Activations