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

    Neuronpedia

    INDEX
    Explanations

    words related to detention or confinement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.88
    manship
    -0.83
    ocene
    -0.79
    #$
    -0.74
    nown
    -0.72
     proportions
    -0.71
     Weasley
    -0.69
     bold
    -0.68
    inventoryQuantity
    -0.68
     fallacy
    -0.68
    POSITIVE LOGITS
    ention
    1.34
    ailed
    1.26
    rans
    1.23
    ected
    1.19
    roit
    1.18
    ector
    1.17
    ective
    1.13
    achable
    1.12
    ection
    1.09
    ainer
    1.08
    Act Density 0.047%

    No Known Activations