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

    Neuronpedia

    INDEX
    Explanations

    words or phrases ending in "t'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yor
    -0.66
     Rampage
    -0.61
     Stuff
    -0.60
     Bulgarian
    -0.60
     tuna
    -0.60
     Moroccan
    -0.60
     convenience
    -0.59
     Blacks
    -0.58
     recycling
    -0.58
     prostitutes
    -0.58
    POSITIVE LOGITS
    ï¸ı
    0.92
    ¯
    0.84
    âĻ
    0.83
    ¯¯
    0.81
    âĶĢ
    0.81
    entity
    0.81
    âĶĢâĶĢ
    0.79
    andise
    0.77
    meric
    0.75
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.75
    Act Density 0.380%

    No Known Activations