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

    Neuronpedia

    INDEX
    Explanations

    phrases related to goals or objectives in a discussion or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pelop
    -0.78
     Monfieur
    -0.72
     Diſ
    -0.70
     houſe
    -0.70
     Houſe
    -0.70
     Chriftian
    -0.69
    
    -0.68
     ſever
    -0.66
     paff
    -0.66
     Shakspeare
    -0.65
    POSITIVE LOGITS
    SequentialGroup
    0.91
    __':
    0.65
     precisar
    0.62
    __":
    0.60
     Dafür
    0.60
    ggings
    0.59
     HttpHeaders
    0.58
     Dazu
    0.58
     위해
    0.56
    ตน
    0.55
    Act Density 0.384%

    No Known Activations