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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dependency or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picchu
    -0.57
    ReusableCell
    -0.55
    ähteet
    -0.52
    Hide
    -0.46
     summed
    -0.45
     cooperating
    -0.45
     stumped
    -0.45
     competed
    -0.45
     assured
    -0.44
    Buff
    -0.44
    POSITIVE LOGITS
    based
    1.51
    BASED
    1.17
    Based
    0.94
    related
    0.81
    oriented
    0.79
    mediated
    0.74
    driven
    0.71
    induced
    0.66
    Oriented
    0.62
     Based
    0.60
    Act Density 0.278%

    No Known Activations