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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism and disagreement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to moral judgments or ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incorpor
    -0.84
     synerg
    -0.79
     targeted
    -0.75
     tyres
    -0.74
     pigeon
    -0.74
     spir
    -0.73
     cloning
    -0.73
     polio
    -0.72
     vulner
    -0.71
     affili
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.42
    âĶĢâĶĢ
    1.29
    ccording
    1.22
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.17
    âĶĢâĶĢâĶĢâĶĢ
    1.13
    Because
    1.06
    à¼
    1.02
    Therefore
    1.02
    ICE
    1.00
    cffffcc
    1.00
    Act Density 0.145%

    No Known Activations