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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures or newspaper names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bl" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.71
    staking
    -0.67
    bub
    -0.62
    DAY
    -0.61
     scratch
    -0.59
     Bing
    -0.58
     Alibaba
    -0.56
    women
    -0.56
     exemptions
    -0.56
    bell
    -0.55
    POSITIVE LOGITS
    anca
    1.10
    eness
    1.06
    ossom
    1.05
    estone
    1.02
    anco
    1.01
    anche
    0.96
    estones
    0.95
    umenthal
    0.91
    anc
    0.91
    ibrary
    0.87
    Act Density 0.036%

    No Known Activations