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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expulsion or being removed from a group or organization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expulsion or removal from a group or place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strument
    -0.81
     fram
    -0.71
     kios
    -0.68
    Fram
    -0.68
    watch
    -0.66
     twilight
    -0.65
     Wat
    -0.64
    Rock
    -0.63
    models
    -0.63
     customization
    -0.63
    POSITIVE LOGITS
     expelled
    3.20
     expel
    2.74
     expulsion
    2.49
     Eps
    1.14
    ipation
    1.07
    pelling
    1.04
     Fuller
    0.96
     banished
    0.93
     Abram
    0.92
     alum
    0.91
    Act Density 0.024%

    No Known Activations