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

    Neuronpedia

    INDEX
    Explanations

    email newsletter subscription offers

    oai_token-act-pair · gpt-3.5-turbo

    references to receiving information via email

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parks
    -0.82
     Corpor
    -0.72
     skiing
    -0.72
     Ath
    -0.70
     CSI
    -0.69
    arks
    -0.68
     Ib
    -0.68
     MLG
    -0.66
    ARK
    -0.65
     ASA
    -0.64
    POSITIVE LOGITS
     inbox
    1.44
    email
    1.02
    ername
    0.98
    inia
    0.92
     Dragonbound
    0.91
     mailbox
    0.88
    arella
    0.86
    romeda
    0.84
    folio
    0.80
    lain
    0.79
    Act Density 0.005%

    No Known Activations