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

    Neuronpedia

    INDEX
    Explanations

    keywords related to terms and conditions, opting out, and receiving updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription management and user consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geist
    -0.84
    roots
    -0.78
    enhagen
    -0.73
    pher
    -0.72
    omorphic
    -0.72
    Pac
    -0.68
    onne
    -0.68
    imer
    -0.67
    abal
    -0.67
    oft
    -0.67
    POSITIVE LOGITS
     MLA
    0.72
     lease
    0.68
     pledge
    0.67
     subscribing
    0.66
     occasional
    0.63
    £ı
    0.63
     polls
    0.63
    ause
    0.62
     parole
    0.61
     rese
    0.60
    Act Density 0.038%

    No Known Activations