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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts involving reasoning, explanations, and justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trunks
    -0.55
     trunk
    -0.54
     дело
    -0.53
    hoppers
    -0.52
    izzle
    -0.52
    IRQn
    -0.51
    ounder
    -0.49
     viri
    -0.49
     Trunk
    -0.48
    SetString
    -0.48
    POSITIVE LOGITS
     therefore
    0.72
    styleType
    0.69
    therefore
    0.68
    MigrationBuilder
    0.68
     dolayı
    0.68
    addCriterion
    0.66
    بوابة
    0.65
    CodedInputStream
    0.64
     therefor
    0.62
    UserScript
    0.61
    Act Density 0.558%

    No Known Activations