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

    Neuronpedia

    INDEX
    Explanations

    words related to dangerous situations or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific Unicode character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incorpor
    -0.82
     manif
    -0.82
     slic
    -0.78
     neighb
    -0.75
     stunts
    -0.72
     tides
    -0.71
     levers
    -0.71
     vulner
    -0.70
     ropes
    -0.70
     surv
    -0.70
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.20
    ï¸ı
    1.18
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.15
    âĶĢâĶĢâĶĢâĶĢ
    1.06
    âĿ
    0.87
    âĸ¬âĸ¬
    0.87
    âĹ
    0.84
     Edited
    0.83
    °
    0.79
    STER
    0.79
    Act Density 0.129%

    No Known Activations