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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political, social, and gaming contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing personal struggle or moral complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Recovery
    -0.74
    Initialized
    -0.73
    rica
    -0.71
    ç¥ŀ
    -0.68
    ometry
    -0.67
    ode
    -0.65
     Compact
    -0.64
     Telescope
    -0.63
     McDonnell
    -0.62
    estone
    -0.61
    POSITIVE LOGITS
    sam
    0.73
    rals
    0.69
    GAN
    0.69
     fuckin
    0.68
     folk
    0.67
    */(
    0.67
     prin
    0.66
     cousin
    0.64
    rat
    0.64
     freak
    0.63
    Act Density 0.258%

    No Known Activations