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

    Neuronpedia

    INDEX
    Explanations

    statements that involve evaluation, opinion, or summaries of a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to connections and relationships between people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cooldown
    -0.55
    externalActionCode
    -0.53
     presidency
    -0.52
     predecessor
    -0.48
     doesnt
    -0.47
    washer
    -0.46
    ishable
    -0.46
    availability
    -0.45
    isSpecialOrderable
    -0.44
    til
    -0.44
    POSITIVE LOGITS
     themselves
    1.13
    selves
    0.87
    their
    0.85
     their
    0.83
     collectively
    0.82
     THEIR
    0.78
    Their
    0.70
     Their
    0.67
     apiece
    0.65
     alike
    0.64
    Act Density 1.395%

    No Known Activations