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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating an increase or comparison in quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commenter
    -0.74
    hai
    -0.68
     itching
    -0.66
    rification
    -0.63
     unveiling
    -0.63
     awarding
    -0.63
    Developer
    -0.62
     tampering
    -0.62
    ¿½
    -0.62
     Employ
    -0.61
    POSITIVE LOGITS
     times
    0.90
     consecut
    0.90
    rarily
    0.85
     efficiently
    0.85
    thin
    0.81
    aciously
    0.79
     stuff
    0.79
     crap
    0.78
     aggressively
    0.78
    heartedly
    0.77
    Act Density 0.327%

    No Known Activations