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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progressive actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "first step" relating to progress or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sins
    -0.81
    itable
    -0.76
    lys
    -0.75
    licted
    -0.73
    ittens
    -0.71
    ores
    -0.70
    asted
    -0.68
     colourful
    -0.68
    olls
    -0.68
     cush
    -0.66
    POSITIVE LOGITS
    step
    0.88
     Steps
    0.87
     toward
    0.85
     steps
    0.83
     step
    0.81
    aphael
    0.80
     towards
    0.79
    Step
    0.78
    steps
    0.76
    dad
    0.74
    Act Density 0.023%

    No Known Activations