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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and taking a stand against law enforcement actions beyond what is necessary

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ML
    -0.55
    ]),
    -0.55
     unexpectedly
    -0.52
    orsi
    -0.51
     ®
    -0.50
    osponsors
    -0.49
    NAS
    -0.49
    awei
    -0.49
    ¶
    -0.48
     beloved
    -0.47
    POSITIVE LOGITS
    )."
    0.65
     gotta
    0.61
     gonna
    0.61
     remorse
    0.60
    .""
    0.60
    anooga
    0.59
    ause
    0.57
     fuckin
    0.56
    .'"
    0.56
     however
    0.56
    Act Density 1.045%

    No Known Activations