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

    Neuronpedia

    INDEX
    Explanations

    special characters, likely for specific formatting or coding purposes

    oai_token-act-pair · gpt-3.5-turbo

    titles of video games or notable references in pop culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.90
     citiz
    -0.88
    aditional
    -0.87
     newcom
    -0.86
     tremend
    -0.77
     newsp
    -0.76
     exting
    -0.74
     thous
    -0.73
     subur
    -0.72
     exha
    -0.71
    POSITIVE LOGITS
    ↵
    0.89
    ³³³³³³³³
    0.86
    ³³³
    0.85
    ³³³³³³³³³³³³³³³³
    0.81
    ̶
    0.79
    Yep
    0.78
    ³³³³
    0.78
    Honestly
    0.76
    Alright
    0.76
    advertising
    0.73
    Act Density 0.400%

    No Known Activations