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

    Neuronpedia

    INDEX
    Explanations

    mentions of rights or freedoms

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating personal rights and freedoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unexpectedly
    -0.77
    asionally
    -0.69
    ktop
    -0.68
     newcomer
    -0.62
    Released
    -0.62
    icipated
    -0.61
    leased
    -0.61
    bitious
    -0.61
     Pebble
    -0.60
    Joined
    -0.59
    POSITIVE LOGITS
     argument
    1.26
     analogy
    1.21
     explanation
    1.19
     reasoning
    1.19
     logic
    1.14
    argument
    1.13
     answer
    1.06
     definitions
    1.04
     definition
    1.04
     arguments
    1.03
    Act Density 0.829%

    No Known Activations