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

    Neuronpedia

    INDEX
    Explanations

    phrases related to production and creation

    oai_token-act-pair · gpt-3.5-turbo

    words related to production or generating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uni
    -0.81
    laus
    -0.76
    hai
    -0.75
    oland
    -0.74
    stra
    -0.74
    istani
    -0.73
    osate
    -0.71
    imb
    -0.69
    rail
    -0.69
    imation
    -0.69
    POSITIVE LOGITS
     offspring
    0.84
     batches
    0.81
     outputs
    0.79
     sparks
    0.73
     goods
    0.72
     usable
    0.70
     plent
    0.70
     enough
    0.68
     domestically
    0.68
    nces
    0.67
    Act Density 0.060%

    No Known Activations