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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or advancement in a process or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey progression or improvement in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fed
    -0.64
    ousse
    -0.60
    tops
    -0.59
    urities
    -0.59
    ateurs
    -0.57
    pots
    -0.57
    dropping
    -0.57
    rices
    -0.56
    atell
    -0.56
    rice
    -0.55
    POSITIVE LOGITS
     route
    0.91
     furthe
    0.81
     lengths
    0.79
     downhill
    0.77
     overboard
    0.73
     bye
    0.72
     unnoticed
    0.69
    ither
    0.69
    WARD
    0.69
     distance
    0.69
    Act Density 0.149%

    No Known Activations