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

    Neuronpedia

    INDEX
    Explanations

    content-related actions and instructions within the context of sharing information and providing guidance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sharing and providing information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hene
    -0.69
    ullah
    -0.68
     imprint
    -0.62
    hea
    -0.61
    utic
    -0.60
    urus
    -0.59
    .?
    -0.57
    taboola
    -0.57
     UNCLASSIFIED
    -0.57
    hei
    -0.56
    POSITIVE LOGITS
    escription
    0.98
     myself
    0.89
     ourselves
    0.81
     Patreon
    0.76
    uploads
    0.72
     excerpts
    0.71
     screenshots
    0.70
    below
    0.69
    endix
    0.68
     ital
    0.68
    Act Density 0.237%

    No Known Activations