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

    Neuronpedia

    INDEX
    Explanations

    phrases related to subscription and calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.11
    3:0.18
    4:0.02
    5:0.03
    6:0.10
    7:0.11
    8:0.05
    9:0.14
    10:0.06
    11:0.10
    Negative Logits
    fer
    -1.36
    enko
    -1.30
    uncture
    -1.24
    renheit
    -1.20
    ornia
    -1.17
    dm
    -1.17
    stad
    -1.17
    miah
    -1.14
    inka
    -1.14
    figured
    -1.12
    POSITIVE LOGITS
     ESV
    1.27
     Sing
    1.11
     subscrib
    1.11
     Random
    1.07
     SPACE
    1.07
     Spotify
    1.05
    Spons
    1.03
     Stronghold
    1.03
     subscriptions
    1.03
     CLS
    1.02
    Act Density 0.002%

    No Known Activations