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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unsubscribing or opting out

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RH
    -0.74
     Drawn
    -0.72
     guiActiveUnfocused
    -0.71
     Corps
    -0.70
     Papers
    -0.69
    RD
    -0.68
    SEA
    -0.68
     Values
    -0.67
     Mavericks
    -0.66
     Median
    -0.66
    POSITIVE LOGITS
     unsub
    1.34
    scribe
    1.20
    stant
    1.06
    mitted
    1.00
    ples
    0.94
    stantial
    0.93
    oshenko
    0.88
    comm
    0.87
    tab
    0.86
    missible
    0.84
    Act Density 0.006%

    No Known Activations