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

    Neuronpedia

    INDEX
    Explanations

    references to violence and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.15
     Garc
    -0.14
    _globals
    -0.14
     visceral
    -0.14
    amina
    -0.14
     Speaker
    -0.13
    бÑĥд
    -0.13
    uito
    -0.13
    .Arg
    -0.13
    503
    -0.13
    POSITIVE LOGITS
     possibility
    0.17
     motive
    0.17
     Explanation
    0.16
     erklä
    0.16
     Accounts
    0.16
     accounts
    0.16
     accounted
    0.15
     account
    0.15
     pars
    0.15
    ingo
    0.15
    Act Density 0.205%

    No Known Activations