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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a growth or increase in something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to increasing trends or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -0.79
     Mub
    -0.78
    pper
    -0.75
    swick
    -0.75
    ioned
    -0.74
    ffe
    -0.72
    ograms
    -0.72
    hra
    -0.72
    atography
    -0.72
    ciplinary
    -0.72
    POSITIVE LOGITS
     pains
    1.17
     impat
    0.91
     momentum
    0.85
     discontent
    0.81
     frustration
    0.80
     realization
    0.78
     awareness
    0.76
     prosperity
    0.75
     annoyance
    0.74
     exponentially
    0.74
    Act Density 0.033%

    No Known Activations