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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology or coding

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     satell
    -0.77
     mathemat
    -0.77
     declining
    -0.76
     controvers
    -0.76
     undermin
    -0.76
     prescriptions
    -0.75
     scattering
    -0.75
     diminishing
    -0.74
     sustaining
    -0.73
     neighb
    -0.73
    POSITIVE LOGITS
    ï¸ı
    1.19
    ttp
    1.08
    ï¸
    1.05
    ¯
    1.03
     è£ıè
    0.98
    âľ
    0.93
    âĢ
    0.91
    âĻ
    0.90
    ðŁĺ
    0.89
    https
    0.87
    Act Density 0.162%

    No Known Activations