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

    Neuronpedia

    INDEX
    Explanations

    names of individuals followed by an action or achievement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Compare
    -0.88
    yz
    -0.83
    protect
    -0.80
    PN
    -0.74
     Compare
    -0.72
    Reviewed
    -0.72
    ISO
    -0.69
    OIL
    -0.69
    opens
    -0.68
    docker
    -0.68
    POSITIVE LOGITS
     eldest
    1.11
     own
    1.07
     grandson
    1.06
     granddaughter
    0.95
     son
    0.95
     successor
    0.94
     daughter
    0.93
    ullivan
    0.92
     hometown
    0.88
     wife
    0.87
    Act Density 0.159%

    No Known Activations