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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discovery and exploration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "discover" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.73
    processing
    -0.70
     negotiators
    -0.68
    cussion
    -0.68
    etimes
    -0.63
     restraining
    -0.63
    itent
    -0.62
     headed
    -0.61
     partic
    -0.61
    nea
    -0.61
    POSITIVE LOGITS
    iveness
    0.98
    ibility
    0.91
    æĥ
    0.88
    ource
    0.87
    ãĤ¦ãĤ¹
    0.87
    çīĪ
    0.86
    æ©
    0.83
    Discover
    0.82
    omething
    0.81
    使
    0.80
    Act Density 0.023%

    No Known Activations