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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accepting terms and conditions for receiving updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to user consent and options for subscription management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oun
    -0.60
    BIL
    -0.58
    cross
    -0.56
    ãĥ¼ãĥĨãĤ£
    -0.54
    BIP
    -0.54
    der
    -0.53
     mole
    -0.53
    DEV
    -0.52
     sabot
    -0.52
    omer
    -0.51
    POSITIVE LOGITS
    SHIP
    0.65
    ceive
    0.60
    Subscribe
    0.59
    ovich
    0.59
    ignty
    0.59
    asp
    0.59
    OVA
    0.57
     Hover
    0.55
     experiment
    0.54
    cedented
    0.53
    Act Density 0.038%

    No Known Activations