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

    Neuronpedia

    INDEX
    Explanations

    items or services followed by a promise of additional options

    oai_token-act-pair · gpt-3.5-turbo

    references to additional content or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.90
    pload
    -0.79
    nikov
    -0.77
    iman
    -0.76
    ãĥ¼ãĥĨ
    -0.73
    cture
    -0.71
    era
    -0.71
    imaru
    -0.70
    Guard
    -0.67
    itudinal
    -0.67
    POSITIVE LOGITS
     importantly
    1.39
     than
    1.05
     goodies
    0.96
     refined
    0.94
     sophisticated
    0.92
     efficient
    0.83
     stringent
    0.82
     exciting
    0.81
     advanced
    0.81
     adventurous
    0.78
    Act Density 0.061%

    No Known Activations