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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions related to a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "detainer"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.78
    manship
    -0.72
    #$
    -0.69
    æł
    -0.67
    ocene
    -0.66
     proportions
    -0.64
     bold
    -0.63
    IDS
    -0.62
     Zamb
    -0.62
    xual
    -0.61
    POSITIVE LOGITS
    ailed
    1.32
    ention
    1.25
    ective
    1.25
    ector
    1.22
    ected
    1.21
    ection
    1.19
    roit
    1.18
    achable
    1.18
    rans
    1.14
    ainer
    1.14
    Act Density 0.027%

    No Known Activations