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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific topic, in this case, Bitcoin and political context

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter "s" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wright
    -0.78
    Alert
    -0.73
     Lauder
    -0.69
    cair
    -0.68
    cloth
    -0.67
    lin
    -0.66
    nn
    -0.66
    thens
    -0.64
     Frie
    -0.64
    hr
    -0.64
    POSITIVE LOGITS
     shortcomings
    1.31
     demise
    1.30
     penchant
    1.26
     propensity
    1.25
     failings
    1.23
     predicament
    1.22
     inability
    1.22
     ability
    1.21
     woes
    1.18
     role
    1.18
    Act Density 0.197%

    No Known Activations