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

    Neuronpedia

    INDEX
    Explanations

    written sentences containing a mix of quotes and opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "wrote" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.81
    illon
    -0.76
    Unity
    -0.69
    icators
    -0.68
    asion
    -0.68
    nel
    -0.68
    ackle
    -0.67
     squared
    -0.67
    Enlarge
    -0.67
    icons
    -0.66
    POSITIVE LOGITS
     memos
    0.80
     eloqu
    0.76
     penned
    0.76
    itatively
    0.75
     furiously
    0.75
     journal
    0.74
     extensively
    0.74
    smanship
    0.74
     letters
    0.72
     scathing
    0.71
    Act Density 0.041%

    No Known Activations