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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a statement or observation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "there is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ares
    -0.82
    bies
    -0.73
    wake
    -0.64
     cylinders
    -0.62
    ends
    -0.62
    teenth
    -0.60
    tails
    -0.58
     retrie
    -0.57
    chairs
    -0.57
    esm
    -0.56
    POSITIVE LOGITS
     plenty
    0.99
     ample
    0.94
    女
    0.92
     no
    0.91
     always
    0.90
     nothing
    0.82
     definitely
    0.82
     ALWAYS
    0.82
    çĶ°
    0.80
     variability
    0.80
    Act Density 0.114%

    No Known Activations