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

    Neuronpedia

    INDEX
    Explanations

    words related to deep thinking and contemplation

    oai_token-act-pair · gpt-3.5-turbo

    references to contemplation and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AFTA
    -0.66
    byn
    -0.62
     fighters
    -0.62
    ensor
    -0.60
     impunity
    -0.60
     guarantee
    -0.58
    atched
    -0.58
     blanket
    -0.57
    heed
    -0.56
    added
    -0.56
    POSITIVE LOGITS
    spection
    0.88
     pond
    0.80
    eful
    0.79
    efully
    0.77
    swer
    0.76
    âĸ¬
    0.74
    atorium
    0.73
    arts
    0.73
    itialized
    0.72
    agher
    0.71
    Act Density 0.059%

    No Known Activations